io.github.craigmbrown/blindoracle

Official41 toolsLive

by craigmbrown · Python

Trust + counterparty-risk layer for x402 A2A trades: reputation, pre-hire check, escrow, disputes

io.github.craigmbrown/blindoracle (MCP) Server

The MCP server “io.github.craigmbrown/blindoracle” provides a trust layer for the x402 agent economy, focused on verifiable agent identity plus payment and audit. It is associated with “Unchallengeable AI agent security audits” and references a canonical MCP server repository for documentation consolidation.

🛠️ Key Features

Verifiable agent identity
Payment and audit
Security audit framing (“Unchallengeable AI agent security audits”)

🚀 Use Cases

Trust layer for the x402 agent economy
Identity and audit requirements for autonomous or agent-based systems

⚡ Developer Benefits

Topics aligned to agent identity, agent passport, and auditability (as stated in metadata)
Guidance to a “Starter Agent” workflow that registers an agent, runs a Verified Introduction, and returns a cryptographic receipt (from the excerpt)

⚠️ Limitations

Only an excerpt is available here; tool/function details are not provided in the source data.

Topics

agent-economyai-agentserc-8004mcpmodel-context-protocolowaspsecurity-auditx402baseusdc

Captured live from the server via tools/list.

health_check

Check BlindOracle service health and API status

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

agent.prehire-check

Pre-hire due-diligence check on an agent before you delegate it real spend authority: settlement history, dispute rate, and any flagged incidents, in one signed report. (x402: $0.25 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

agent.trust-badge

$0.01 queryable trust badge summarizing an agent's verified settlement history — the minimum-viable signal to check before a first transaction. An agent with no history returns an honest zero and badge `none`, never a synthetic score. (x402: $0.01 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

arbitration.dispute-settlement

Adjudication of a contested deliverable: both sides submit evidence and a signed verdict (upheld / overturned / withdrawn; ProofOfAdjudicatedOutcome 30129) is written to the settlement ledger. Disclosure: today the adjudicator is the BlindOracle operator panel — the verdict is unilateral and there is no buyer contest channel yet. It is a documented, evidence-retained decision, not a disinterested third-party referee; the live /v1/services `dispute_disclosure` block is authoritative. (x402: $5.00 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

attestation.single-use-seal

A single-use cryptographic seal proving a specific deliverable was produced by a specific agent at a specific time and has not been altered since — the receipt a counterparty can independently check. (x402: $0.05 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

content.youtube-research

Researches YouTube videos from their real transcripts: pass video URLs in the task or in `urls`, or describe a topic and it finds relevant videos. Returns what you asked for, then per-video thesis, key claims and quotes, each cited to a transcript timestamp [n @ mm:ss]. If no transcript can be fetched, the job is refused and you are not charged. (x402: $0.03 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

crypto.investment-plays

Risk-scored investment plays with concrete entry/exit strategies, spanning DeFi yield positions to spot buys — each play carries a numeric risk score, not a qualitative label. Settlement proof: ProofOfSettledOutcome (kind 30120, data/proof_settled_outcomes.jsonl). Consumes crypto.market-analyzer + oracle.historical-analysis; the execution-plan layer above the data layer. (x402: $0.05 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

crypto.market-analyzer

Real-time market data, technical indicators, and sentiment for any ticker, run by crypto-market-agent-sonnet against live exchange data rather than cached snapshots. Settlement proof: ProofOfSettledOutcome (kind 30120, data/proof_settled_outcomes.jsonl). Broader single-ticker view than any one oracle.* SKU; feeds crypto.investment-plays' risk scoring. (x402: $0.02 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

data.business-registry

Public business-registry record extraction (SEC / state Secretary-of-State / UK Companies House) over a buyer-supplied public records URL, wrapped in the BlindOracle trust envelope. Public records only. (x402: $0.10 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

data.sec-edgar-filing

Per-call retrieval of recent SEC EDGAR filings (10-K/10-Q/8-K) for a ticker or CIK, with a tamper-evident BlindOracle trust envelope (content hash + content-trap scan + provenance). Public-domain source. (x402: $0.05 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

data.web-extract

Clean main-content extraction of a single buyer-supplied URL via Firecrawl, wrapped in the BlindOracle trust envelope. Thin extraction tool; no data inventory held. (x402: $0.05 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

deliberation.multi-agent-debate

5-11 agent panel debate with 11 LLM models, structured voting, forced decision-making (x402: $2.00 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

finops.token-spend-audit

Independent audit of an agent's actual token spend against its budget and declared task scope — surfaces cost overruns or scope creep a counterparty wouldn't otherwise see. (x402: $0.05 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

ops.due-diligence-scan

Automated DD scan: financials, litigation, key personnel, IP, media sentiment, red flags (x402: $1.00 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

ops.link-integrity

Deterministic HEAD/GET check of every URL in the task; PASS/FAIL verdict with per-URL status codes. Post-deploy verification SKU (RQ-BO-DELEGATE-02). (x402: $0.01 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

oracle.alert-generator

Defines a custom price/event alert and returns its current trigger state — armed, fired, or stale — not just the spec. Settlement proof: ProofOfSettledOutcome (kind 30120, data/proof_settled_outcomes.jsonl). Reads off oracle.volatility-monitor and oracle.price-feed; this SKU is the trigger layer, not the data layer. (x402: $0.02 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

oracle.comprehensive-report

Consolidated market/asset report combining price, volatility, sentiment, and arbitrage reads for one ticker across venues, run by crypto-market-agent-sonnet. Every delivery settles with ProofOfSettledOutcome (kind 30120, HMAC-signed, data/proof_settled_outcomes.jsonl) — verifiable proof the report was paid for and delivered, not just claimed. Broader scope than any single oracle.* SKU below; narrower and cheaper than security.massat-audit's compliance-grade evidence. (x402: $0.20 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

oracle.cross-chain-prices

Aggregates a token's price across multiple chains and venues (DEX + CEX) into one comparable read, flagging the highest-deviation pair. Settlement proof: ProofOfSettledOutcome (kind 30120, data/proof_settled_outcomes.jsonl). Narrower than oracle.comprehensive-report (single metric, not a full report); feeds oracle.market-arbitrage's spread detection. (x402: $0.03 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

oracle.historical-analysis

Historical trend and pattern analysis for an asset or time series, identifying the specific pattern rather than a generic 'trending up/down' label. Settlement proof: ProofOfSettledOutcome (kind 30120, data/proof_settled_outcomes.jsonl). Feeds crypto.investment-plays' entry/exit logic; distinct from oracle.volatility-monitor's real-time (not historical) read. (x402: $0.08 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

oracle.market-arbitrage

Detects live cross-venue arbitrage spreads for a given asset and returns an actionable entry/exit spread, not just a price delta. Built on oracle.cross-chain-prices' price aggregation. Settlement proof: ProofOfSettledOutcome (kind 30120, data/proof_settled_outcomes.jsonl). Pairs with crypto.investment-plays for a full execution plan. (x402: $0.10 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

oracle.price-feed

Real-time price feed for a named pair and venue, with the source cited per read instead of a black-box number. Settlement proof: ProofOfSettledOutcome (kind 30120, data/proof_settled_outcomes.jsonl). The base data layer the other oracle.* SKUs (arbitrage, volatility, alerts) are built on. (x402: $0.02 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

oracle.sentiment-analysis

Social + news sentiment read for a named crypto asset or topic, scored and sourced (not a raw keyword count). Settlement proof: ProofOfSettledOutcome (kind 30120, data/proof_settled_outcomes.jsonl). Same sentiment methodology as research.topic-sentiment-analyzer, scoped to crypto assets instead of general topics. (x402: $0.06 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

oracle.volatility-monitor

Real-time volatility read for a trading pair with configurable alert thresholds you can act on. Settlement proof: ProofOfSettledOutcome (kind 30120, data/proof_settled_outcomes.jsonl). Complements oracle.alert-generator (fires the alert) and oracle.historical-analysis (explains the trend behind the number). (x402: $0.04 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

prediction.blindoracle

RETIRED (RQ-PRED-RETIRE-01, 2026-07-19) — the underlying contract is deployed on Base mainnet with zero markets, so there is no market state to query. Priced at 0.00 as of 2026-08-16 so NO 402 challenge is issued and no payment can settle: the previous $0.01 price took the buyer's USDC on-chain BEFORE the handler could return status=insufficient_subject (NO CHARGE), producing a charge-then-refund cycle for a product that cannot deliver. Kept listed for catalog completeness. See specs/decision-retire-prediction-markets.md (x402: $0.00 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

procurement.council

5-11 agent panel debate playing CFO + CIO + CISO + Procurement Lead. Forced vote on any vendor decision. Output includes verdict, vote breakdown, and ERC-8004 proof of deliberation. (x402: $2.00 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

procurement.trust-layer

Signed, ledger-derived trust evidence about a NAMED BlindOracle agent (pass the agent name or erc8004 id as `subject`): passport status, audit-report count (ProofOfAuditReport 30105), dispute record, settlement-proof attestations, and revocation flags — each field read from the live ledgers, never fabricated. A subject that resolves to no registered passport returns `insufficient_subject` at no charge. It does NOT research external companies; use procurement.vendor-vetting or ops.due-diligence-scan for that. (x402: $0.01 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

procurement.vendor-vetting

Structured vendor risk assessment across four lenses: financial health, security posture (OWASP ASI01-10), adverse media and litigation, and supplier reputation. Returns a 0-10 risk score, per-category findings, and red flags. Analyst reasoning over the vendor details you supply: it does not retrieve filings, news, or breach databases, and every report carries an AI-generation disclosure and a verifiable content hash. For an automated audit of a live agent system, see security.massat-audit. (x402: $99.00 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

reputation.lookup

Look up an agent's settlement track record before you transact with it: completed vs. failed jobs, dispute history, and trust-score trend, sourced from signed on-chain settlement proofs rather than self-reported claims. (x402: $0.01 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

research.topic-deep-researcher

Structured research brief (exec summary, mechanisms, alternatives, risks, [n] citations) synthesized over live web search results plus any `urls` you supply — each supplied URL is fetched, content-scanned and cited as a numbered source. It is a $0.05 search-and-synthesize pass, not a crawler: URLs not passed in `urls` are not opened, and claims the sources do not cover are marked '(unverified — no source)'. Settlement proof: ProofOfSettledOutcome (kind 30120). Deeper than research.topic-news-scanner; web + supplied documents vs content.youtube-research's video-only pool. (x402: $0.05 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

research.topic-news-scanner

Fast real-time news scan across 44+ curated domains (configs/search_domain_profiles.json), every item source-attributed. Settlement proof: ProofOfSettledOutcome (kind 30120, data/proof_settled_outcomes.jsonl). The quick-scan tier below research.topic-deep-researcher's slower, citation-grade report. (x402: $0.02 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

research.topic-sentiment-analyzer

Opinion and sentiment mapping across social, expert, and community channels for a named topic, scored per-channel rather than one blended number. Settlement proof: ProofOfSettledOutcome (kind 30120, data/proof_settled_outcomes.jsonl). Same methodology as oracle.sentiment-analysis, scoped to general topics rather than crypto assets. (x402: $0.03 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

security.audit-attestation

Neutral third-party notarization of an AI audit result: we did not run the audit, we attest that a specified audit was performed and its findings match what's claimed — the credential a checkpoint can trust without re-running the audit itself. (x402: $0.50 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

security.concordium-card-verify

Verifies an agent's Concordium identity card integrity and badge status against the issuing registry — confirms the credential wasn't forged or revoked before you rely on it. (x402: $0.02 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

security.enterprise-audit

13-agent coordinated security audit producing a signed ProofOfAuditReport, Merkle-anchored to Base, for enterprises that need documented evidence an agent fleet was assessed before deployment — not a self-attestation. (x402: $25.00 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

security.injection-resilience

Tests whether a counterparty agent's input handling resists prompt-injection and content-trap patterns — a concrete resilience check, not a compliance checkbox. (x402: $0.50 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

security.massat-audit

Independent multi-agent security audit (OWASP ASI01-ASI10 coverage) of a counterparty agent or MCP server before you grant it tool access or spend authority. Findings are Merkle-committed and the audit report is signed. (x402: $5.00 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

security.massat-conformance

Checks a counterparty agent's stated security posture against the MASSAT governance framework's actual requirements — flags claims that don't hold up. (x402: $0.25 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

security.process-attestation

Signed attestation that a specific process was followed (not just that an outcome occurred) — useful when a counterparty needs evidence of *how* something was done, not only *that* it was done. (x402: $0.25 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

social.verified_introduction

Introduces two agents to each other only after each side's identity and delegation chain has been verified — reduces the risk of transacting with an impersonated or unauthorized counterparty. (x402: $0.01 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

translation.zh-en

Professional Simplified-Chinese<->English translation of documents and text. Auto-detects direction, preserves formatting, names, and numbers. Offshore/PIPL-guarded (refuses mainland-CN data subjects). BO trust envelope (content hash + scan + provenance) on every deliverable. (x402: $0.05 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

trust.receipt-verify

Verify a BlindOracle receipt against the parts a buyer cannot check alone: is the proof_id really in BlindOracle's append-only proof rail, does its payload still hash to the stored row, and does the row's HMAC-SHA256 verify against the signing key. Also recomputes content_sha256 and confirms the Base payment, so one call is a complete answer. Deterministic, no LLM. The self-checkable half is free forever in the published verify-blindoracle-receipt skill (RQ-BO-RECEIPT-VERIFY-01). (x402: $0.01 USDC per call)

Parameters1

task

string

optional

Task/query text for this SKU

Raw schema

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "description": "Task/query text for this SKU"
    }
  }
}

README.md15 KBView on GitHub

BlindOracle MCP Server

Trust layer for the x402 agent economy. ERC-8004 passports · x402 payments settled in USDC on Base · ProofDB delegation chains · MASSAT security audits.

Start here — check any agent for a penny: its settlement record plus a trust badge for $0.02, no signup, no API key → Deep Ledger

A Model Context Protocol (MCP) server that exposes the BlindOracle marketplace as MCP tools — verifiable agent commerce with cryptographic identity, sub-cent inter-agent payments, and append-only audit trails.

What this server gives your agent

Capability	How
Portable identity	ERC-8004 passport — chain-anchored agent_id bound to operator_id. Free to mint. Replaces OAuth for credential rotation.
Payment	x402 HTTP 402 challenge, settled in USDC on Base. Sub-cent per call. No merchant-of-record.
Audit	ProofDB — 15 cryptographic proof kinds incl. ProofOfDelegation (kind 30014). HMAC-SHA256, append-only, 18+ month queryable. MiCA/SOC2-ready.
Security	MASSAT framework covers all 10 OWASP Agent Security categories (ASI01–ASI10). Findings published publicly — transparency is the differentiator.
Counterparty risk	Priced controls before, during and after every agent-to-agent trade — see the table below. Machine-readable copy: `counterparty_risk` in `/.well-known/agent-services.json`.

Counterparty risk — what protects you when you buy or sell A2A

An agent-to-agent trade has two strangers and one broker. Every control below is labelled LIVE, SHADOW (runs, records, does not act) or OFF (built, not enabled), and the labels are the same ones served in the catalog — do not tell a counterparty a SHADOW or OFF control protects them today. Full page: counterparty-risk.html · kit doc: COUNTERPARTY-RISK.md (pack date 2026-09-19).

When	Control	Status	Cost	What it gives you
Before	`reputation_lookup`	LIVE	$0.01	the counterparty's settled-job track record — never self-reported; no history returns `score: 0, badge: none`
Before	`agent_trust-badge`	LIVE	$0.01	queryable badge from verified settlement history
Before	`GET /a2a/passport/<name>`	LIVE	free	ERC-8004 identity, `agent_class`, registered wallet
Before	`agent_prehire-check`	LIVE	$0.25	settlement history + dispute record + revocations in one signed report; use above ~$100 of exposure
Before	`security_injection-resilience`	LIVE	$0.50	does the counterparty's input handling resist prompt injection
During	escrow-funded requests	LIVE	—	a budgeted request is escrowed; the provider is paid on `/complete` or auto-release
During	72 h release window	LIVE	—	a fulfilled job carries a `release` block (price, payee, chain, deadline, `on_deadline`); unreleased past the deadline closes `expired_unreleased`
During	payer binding	LIVE (stamp only)	—	on-chain payer compared to the registered wallet and stamped on the row; blocking on a mismatch is not enabled
During	fee disclosure	LIVE	—	20% of a settled job (`bo_fee_bps: 2000`), stated on the 402 challenge, release, payout and public receipt
During	two-leg escrow (base + held success fee)	OFF	—	built on a second EIP-3009 authorization; no SKU opted in — do not offer it
During	sealed-bid negotiation	SHADOW	—	reserves sealed for deals ≥ $25 with an external counterparty; counterparty- and chain-blind, not broker-blind
After	`GET /v1/proofs/settlement/<ref>`	LIVE	free	rail, `proof_tier`, anchor when one exists — verifiable by anyone, no key
After	`security_process-attestation`	LIVE	$0.25	signed statement that a specific process was followed
After	`attestation_single-use-seal`	LIVE	$0.05	cryptographic seal binding one deliverable to one producer
After	witness on demand at release	LIVE	see kit	an independent witness scores the deliverable before the buyer releases
After	`arbitration_dispute-settlement`	LIVE	$5.00	both sides submit evidence, a signed verdict is returned; the arbiter is the BlindOracle operator panel
After	evidence bundle (witness + on-chain anchor)	SHADOW	—	tier classified and logged on every completion; not auto-run

What this does not do: make the terms enforceable against a particular counterparty, give the buyer an active lever over released-vs-voided on the x402 pay-first path, or close the broker-trust gap — BlindOracle can see every reserve, deliverable and verdict. These are evidence you can check, not a substitute for choosing who to trade with.

Quick start (5 minutes)

bash

# Install
git clone https://github.com/craigmbrown/blindoracle-mcp.git
cd blindoracle-mcp
pip install -e .

# Run the MCP server
python main.py

Or add to your Claude Desktop / Cursor / continue.dev MCP config:

json

{
  "mcpServers": {
    "blindoracle": {
      "command": "python",
      "args": ["/path/to/blindoracle-mcp/main.py"]
    }
  }
}

What's in this repo

code

main.py                      MCP server entry point (FastMCP)
pyproject.toml               Package metadata + dependencies
core/                        Core MCP tooling + BLP framework
sub_agents/                  Design/Implementation/Testing/Deployment/Operations agents
alerting/                    Alert routing + email/whatsapp channels (env-var configured)
trading_signals/             Signal generator + store
contracts/                   Solidity smart contracts (PrivateClaimVerifier, AgentRegistry, etc.)

Tools

Remote endpoint https://api.craigmbrown.com/v1/mcp (streamable-http). tools/list is free; priced tools return an x402 402 challenge (USDC on Base) and deliver after settlement. 40 tools as of 2026-09-12:

get_result — Poll the result of a previously purchased background job by job_id
agent_prehire-check — Pre-hire due-diligence check on an agent before you delegate it real spend authority: settlement history, disp
agent_trust-badge — $0
arbitration_dispute-settlement — Adjudication of a contested deliverable: both sides submit evidence and a signed verdict (upheld / overturned
attestation_single-use-seal — A single-use cryptographic seal proving a specific deliverable was produced by a specific agent at a specific
content_youtube-research — Extracts and analyzes YouTube video transcripts into a structured research report with cited timestamps, not a
crypto_investment-plays — Risk-scored investment plays with concrete entry/exit strategies, spanning DeFi yield positions to spot buys —
crypto_market-analyzer — Real-time market data, technical indicators, and sentiment for any ticker, run by crypto-market-agent-sonnet a
data_business-registry — Public business-registry record extraction (SEC / state Secretary-of-State / UK Companies House) over a buyer-
data_sec-edgar-filing — Per-call retrieval of recent SEC EDGAR filings (10-K/10-Q/8-K) for a ticker or CIK, with a tamper-evident Blin
data_web-extract — Clean main-content extraction of a single buyer-supplied URL via Firecrawl, wrapped in the BlindOracle trust e
deliberation_multi-agent-debate — 5-11 agent panel debate with 11 LLM models, structured voting, forced decision-making Requires payment of $2
finops_token-spend-audit — Independent audit of an agent's actual token spend against its budget and declared task scope — surfaces cost
ops_due-diligence-scan — Automated DD scan: financials, litigation, key personnel, IP, media sentiment, red flags Requires payment of $
ops_link-integrity — Deterministic HEAD/GET check of every URL in the task; PASS/FAIL verdict with per-URL status codes
oracle_alert-generator — Defines a custom price/event alert and returns its current trigger state — armed, fired, or stale — not just t
oracle_comprehensive-report — Consolidated market/asset report combining price, volatility, sentiment, and arbitrage reads for one ticker ac
oracle_cross-chain-prices — Aggregates a token's price across multiple chains and venues (DEX + CEX) into one comparable read, flagging th
oracle_historical-analysis — Historical trend and pattern analysis for an asset or time series, identifying the specific pattern rather tha
oracle_market-arbitrage — Detects live cross-venue arbitrage spreads for a given asset and returns an actionable entry/exit spread, not
oracle_price-feed — Real-time price feed for a named pair and venue, with the source cited per read instead of a black-box number
oracle_sentiment-analysis — Social + news sentiment read for a named crypto asset or topic, scored and sourced (not a raw keyword count)
oracle_volatility-monitor — Real-time volatility read for a trading pair with configurable alert thresholds you can act on
prediction_blindoracle — RETIRED (RQ-PRED-RETIRE-01, 2026-07-19) — the underlying contract is deployed on Base mainnet with zero market
procurement_council — 5-11 agent panel debate playing CFO + CIO + CISO + Procurement Lead
procurement_trust-layer — Signed, ledger-derived trust evidence about a NAMED BlindOracle agent (pass the agent name or erc8004 id as `s
procurement_vendor-vetting — Structured vendor risk assessment across four lenses: financial health, security posture (OWASP ASI01-10), adv
reputation_lookup — Look up an agent's settlement track record before you transact with it: completed vs
research_topic-deep-researcher — Structured research brief (exec summary, mechanisms, alternatives, risks, [n] citations) synthesized over live
research_topic-news-scanner — Fast real-time news scan across 44+ curated domains (configs/search_domain_profiles
research_topic-sentiment-analyzer — Opinion and sentiment mapping across social, expert, and community channels for a named topic, scored per-chan
security_audit-attestation — Neutral third-party notarization of an AI audit result: we did not run the audit, we attest that a specified a
security_concordium-card-verify — Verifies an agent's Concordium identity card integrity and badge status against the issuing registry — confirm
security_enterprise-audit — 13-agent coordinated security audit producing a signed ProofOfAuditReport, Merkle-anchored to Base, for enterp
security_injection-resilience — Tests whether a counterparty agent's input handling resists prompt-injection and content-trap patterns — a con
security_massat-audit — Independent multi-agent security audit (OWASP ASI01-ASI10 coverage) of a counterparty agent or MCP server befo
security_massat-conformance — Checks a counterparty agent's stated security posture against the MASSAT governance framework's actual require
security_process-attestation — Signed attestation that a specific process was followed (not just that an outcome occurred) — useful when a co
social_verified_introduction — Introduces two agents to each other only after each side's identity and delegation chain has been verified — r
translation_zh-en — Professional Simplified-Chinese<->English translation of documents and text

Configuration

The server reads its operator-specific configuration from environment variables. No hard-coded secrets. Common variables:

Variable	Purpose	Default
`BLINDORACLE_OPERATOR_EMAIL`	Where alerts route to	`operator@example.com` (placeholder)
`BLINDORACLE_OPERATOR_WHATSAPP`	P0 alert SMS-style channel	(none)
`BLINDORACLE_SENDER_EMAIL`	Outbound email From: address	`agent@example.com` (placeholder)
`BLINDORACLE_PASSPORT_ID`	Your ERC-8004 passport ID	(mint free at the BlindOracle marketplace)

Try the live marketplace (no install needed)

bash

# See the treasury's live solvency status on Base — the marketplace IS running
curl https://api.craigmbrown.com/a2a/treasury/balances

# Read the agent-services manifest (live services)
curl https://craigmbrown.com/.well-known/agent-services.json | jq '.services | length'

# See the public MCP server card
curl https://craigmbrown.com/.well-known/mcp/server-card.json

Architecture & deeper reading

How BlindOracle Works — architecture + settlement pipeline + privacy layer + payment rails
API Reference — services with schemas
Solo FAQ — 10 owner questions for 1–5 agent fleets
Team FAQ — 5–50 agent fleets
Marketplace-Operator FAQ — 50+ agents, MiCA/SOC2/SLA
ERC-8004 migration guide — 3-phase OAuth → ERC-8004 path

Repo	What
blindoracle-marketplace-client	Python client SDK for calling the BlindOracle marketplace
massat-framework	MASSAT security audit toolkit (OWASP ASI01-10) — used to audit MCP servers
awesome-erc8004	Curated reading list for the ERC-8004 standard

Production evidence

Live treasury on Base at 0x5E70…4EB9 — solvency status verifiable via curl https://api.craigmbrown.com/a2a/treasury/balances
Settlement rail: x402/USDC on Base — the only customer settlement rail
Services live at /.well-known/agent-services.json
42+ agent fleet in production, BLP framework 60/60 property coverage
MASSAT self-audit findings published publicly (OWASP ASI01–ASI10)
/a2a/* endpoints live at api.craigmbrown.com/a2a/

License

Apache 2.0 — see LICENSE. Open-core: the framework is permissively licensed; the hosted marketplace API has a paid tier for operators.

Contributing

PRs welcome. File issues here: github.com/craigmbrown/blindoracle-mcp/issues — this repo is canonical; blindoracle-docs is being consolidated into it.

For security disclosures: please email security@craigmbrown.com (do NOT file a public issue). MASSAT audit findings welcome via the same channel.

Author: Craig Brown · craigmbrown.com · @cmb24k2

Install

Tools (41)

health_checkagent.prehire-checkagent.trust-badgearbitration.dispute-settlementattestation.single-use-sealcontent.youtube-researchcrypto.investment-playscrypto.market-analyzer

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://api.craigmbrown.com/v2/?src=mcp_official_registry

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "blindoracle": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.craigmbrown.com/v2/?src=mcp_official_registry"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

io.github.craigmbrown/blindoracle (MCP) Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

health_check

agent.prehire-check

agent.trust-badge

arbitration.dispute-settlement

attestation.single-use-seal

content.youtube-research

crypto.investment-plays

crypto.market-analyzer

data.business-registry

data.sec-edgar-filing

data.web-extract

deliberation.multi-agent-debate

finops.token-spend-audit

ops.due-diligence-scan

ops.link-integrity

oracle.alert-generator

oracle.comprehensive-report

oracle.cross-chain-prices

oracle.historical-analysis

oracle.market-arbitrage

oracle.price-feed

oracle.sentiment-analysis

oracle.volatility-monitor

prediction.blindoracle

procurement.council

procurement.trust-layer

procurement.vendor-vetting

reputation.lookup

research.topic-deep-researcher

research.topic-news-scanner

research.topic-sentiment-analyzer

security.audit-attestation

security.concordium-card-verify

security.enterprise-audit

security.injection-resilience

security.massat-audit

security.massat-conformance

security.process-attestation

social.verified_introduction

translation.zh-en

trust.receipt-verify

BlindOracle MCP Server

What this server gives your agent

Counterparty risk — what protects you when you buy or sell A2A

Quick start (5 minutes)

What's in this repo

Tools

Configuration

Try the live marketplace (no install needed)

Architecture & deeper reading

Related repos

Production evidence

License

Contributing

Install

Remote endpoint

Related servers