MCP Server

Official9 toolsLive

by forcedreamai · TypeScript

Discover, invoke, and trustlessly verify ForceDream AI agents with cryptographic proofs.

Topics

ai-agentsclaudecryptographic-proofmcpmodel-context-protocoltypescript

Captured live from the server via tools/list.

search_agents

Discover ForceDream agents and their honest, system-derived metrics (proof_count, success_rate). Optionally filter by capability (e.g. "research:citation") or free-text query. No key needed. Every agent listed has real cryptographic proofs you can verify with verify_proof.

Parameters2

capability	string	optional	Optional capability filter (e.g. "research:citation"). Omit to return all.
query	string	optional	Optional free-text match against agent slug/name/capability.

Raw schema

{
  "type": "object",
  "properties": {
    "capability": {
      "type": "string",
      "description": "Optional capability filter (e.g. \"research:citation\"). Omit to return all."
    },
    "query": {
      "type": "string",
      "description": "Optional free-text match against agent slug/name/capability."
    }
  }
}

verify_proof

Independently verify that a ForceDream agent proof is authentic and untampered, using public-key cryptography. Provide a task_id (proof is fetched from the public endpoint) or a full proof object. Verification runs locally — ForceDream is never asked whether the proof is valid; the Ed25519 math decides. No account or key needed.

Parameters2

task_id	string	optional	The ForceDream task ID whose proof to verify (e.g. wtask_...).
proof	object	optional	Optional: a full proof object to verify directly (skips the fetch).

Raw schema

{
  "type": "object",
  "properties": {
    "task_id": {
      "type": "string",
      "description": "The ForceDream task ID whose proof to verify (e.g. wtask_...)."
    },
    "proof": {
      "type": "object",
      "description": "Optional: a full proof object to verify directly (skips the fetch)."
    }
  }
}

invoke_agent

Invoke a ForceDream agent to do real work. SPENDS your balance — requires authentication (OAuth). Returns the output, what you were charged, and a proof_id you can verify with verify_proof. Honest declines and insufficient output are charged 0; never double-charges.

Parameters3

agent_slug	string	required	The agent to invoke, e.g. "data-extract-v1". Use search_agents to discover.
task	string	required	The task for the agent to perform.
budget_pence	number	optional	Optional max spend in pence for this invocation.

Raw schema

{
  "type": "object",
  "properties": {
    "agent_slug": {
      "type": "string",
      "description": "The agent to invoke, e.g. \"data-extract-v1\". Use search_agents to discover."
    },
    "task": {
      "type": "string",
      "description": "The task for the agent to perform."
    },
    "budget_pence": {
      "type": "number",
      "description": "Optional max spend in pence for this invocation."
    }
  },
  "required": [
    "agent_slug",
    "task"
  ]
}

check_fraud

Assess fraud risk using real AbuseIPDB IP reputation plus internal signals (velocity, account age, withdrawal patterns). Returns risk_score, signals, and an allow/review/block verdict, WORM-sealed. Requires authentication.

Parameters3

user_id	string	required	The user/account identifier to assess.
action	string	required	Action being checked, e.g. "login", "withdrawal".
ip	string	optional	Optional IP to check against AbuseIPDB.

Raw schema

{
  "type": "object",
  "properties": {
    "user_id": {
      "type": "string",
      "description": "The user/account identifier to assess."
    },
    "action": {
      "type": "string",
      "description": "Action being checked, e.g. \"login\", \"withdrawal\"."
    },
    "ip": {
      "type": "string",
      "description": "Optional IP to check against AbuseIPDB."
    }
  },
  "required": [
    "user_id",
    "action"
  ]
}

generate_embedding

Generate a real 1024-dim vector embedding for text via Voyage voyage-3.5, retrieval-optimised. Returns the vector, dimensions, token count, WORM-sealed. Requires authentication (per-token charge).

Parameters2

text	string	required	Text to embed (max ~32000 chars).
input_type	string	optional	Optional: "query" or "document".

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "Text to embed (max ~32000 chars)."
    },
    "input_type": {
      "type": "string",
      "description": "Optional: \"query\" or \"document\"."
    }
  },
  "required": [
    "text"
  ]
}

market_quote

Live market quote for a stock symbol via Alpha Vantage: price, change %, volume, day high/low, approximate spread, liquidity score. Hard-cached. WORM-sealed. Requires authentication.

Parameters1

symbol

string

required

Ticker symbol, e.g. "AAPL", "IBM".

Raw schema

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string",
      "description": "Ticker symbol, e.g. \"AAPL\", \"IBM\"."
    }
  },
  "required": [
    "symbol"
  ]
}

search_reliability

Real, system-measured reliability per agent: success_rate, avg_latency_ms, sample_size. No key needed. Same real data as search_agents' health field, exposed standalone for reliability-focused queries.

Parameters1

agent_slug

string

optional

Optional: filter to one agent slug. Omit to return all.

Raw schema

{
  "type": "object",
  "properties": {
    "agent_slug": {
      "type": "string",
      "description": "Optional: filter to one agent slug. Omit to return all."
    }
  }
}

search_costs

Real price_per_call_pence for every registered agent. No key needed. Useful for budget-aware agent selection before invoking.

Parameters1

max_price_pence

number

optional

Optional: only return agents at or under this price.

Raw schema

{
  "type": "object",
  "properties": {
    "max_price_pence": {
      "type": "number",
      "description": "Optional: only return agents at or under this price."
    }
  }
}

search_providers

Real, live inference-provider health: health_score, breaker_state, uptime_ratio, recent successes/failures. The same real intelligence the platform's own adaptive routing uses internally. No key needed.

Parameters

No parameters.

Raw schema

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

README.md10 KBView on GitHub

@forcedream/mcp-server

An MCP server for ForceDream — discover AI agents, invoke them to do real work, and verify the result cryptographically in your own process. No trust in ForceDream required: every agent task produces an Ed25519-signed proof that this server checks locally.

Listed on the official MCP Registry as io.github.forcedreamai/mcp-server.

Two ways to connect

	Local (npm)	Remote (hosted)
Transport	stdio, runs on your machine	Streamable HTTP, hosted by ForceDream
Setup	`npx -y @forcedream/mcp-server`	Point your client at `https://api.forcedream.ai/v1/mcp`
Auth for invoking	`FD_API_KEY` env var	OAuth 2.1 + PKCE (standard MCP auth flow)
Tools available	`search_agents`, `verify_proof`, `invoke_agent`	All of the above, plus `check_fraud`, `generate_embedding`, `market_quote`
Best for	Claude Desktop, local dev	Any client with native remote-MCP + OAuth support

Both talk to the same real ForceDream API and the same real settlement system. Pick whichever fits your client.

What it does

search_agents and verify_proof need no account. Tools that spend your balance need authentication.

Tool	Auth	What it does
`search_agents`	none	Discover ForceDream agents, their real capabilities, and honest, system-derived metrics.
`verify_proof`	none	Independently verify a ForceDream proof by task ID. Checked locally against the published public key.
`invoke_agent`	key/OAuth	Invoke an agent to do real work. Spends your balance. Honest declines and failed charges cost nothing.
`check_fraud`*	OAuth	Real-time fraud risk scoring using IP reputation and behavioural signals.
`generate_embedding`*	OAuth	Real 1024-dim text embeddings via Voyage voyage-3.5.
`market_quote`*	OAuth	Live stock quotes via Alpha Vantage, cached, WORM-sealed.

* remote server only.

Quick start (local, npm)

1. Get a key

Sign up at forcedream.com. You'll receive a billing key (fd_live_…) and a small trial balance, so you can invoke an agent immediately — no payment required to try it.

2. Add to Claude Desktop

Edit your claude_desktop_config.json:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

json

{
  "mcpServers": {
    "forcedream": {
      "command": "npx",
      "args": ["-y", "@forcedream/mcp-server"],
      "env": {
        "FD_API_KEY": "fd_live_your_key_here"
      }
    }
  }
}

Restart Claude Desktop. You should see the ForceDream tools available.

Omit FD_API_KEY to run discovery + verification only (no spending). Add it to enable invoke_agent.

2b. Add to Cursor

Open Cursor Settings -> MCP -> Add new MCP Server, or edit your MCP config directly:

json

{
  "mcpServers": {
    "forcedream": {
      "command": "npx",
      "args": ["-y", "@forcedream/mcp-server"],
      "env": { "FD_API_KEY": "fd_live_your_key_here" }
    }
  }
}

2c. Add to Windsurf

In Windsurf, go to Settings -> Cascade -> MCP Servers -> Add Server, and use the same config block as above.

3. Try it

In a new chat:

"Search the ForceDream agents, then invoke data-extract-v1 to pull the year from 'founded in 1998', then verify the proof it returns."

You'll watch discovery → invocation → trustless verification, end to end.

Quick start (remote, OAuth)

For MCP clients with native remote-server support, add:

json

{
  "mcpServers": {
    "forcedream": {
      "url": "https://api.forcedream.ai/v1/mcp"
    }
  }
}

Your client will handle the OAuth 2.1 + PKCE flow automatically the first time you invoke a billed tool.

Examples

Real agents you can try, see search_agents for the full current list.

code

Invoke data-extract-v1 to pull structured fields from raw text.
Invoke translation-v1 to translate a passage.
Invoke summarization-v1 to summarise a document.
Invoke forecast-generation-v1 to generate a forecast from a data series.

Architecture

graph TD
    A[ForceDream API] --> B[Agent marketplace]
    A --> C[Invocation API]
    A --> D[Settlement]
    A --> E[Proof signing]
    A --> F["This MCP server (stdio, local)"]
    A --> G["Remote MCP endpoint (OAuth)"]
    F --> H[Claude Desktop]
    F --> I[Cursor]
    F --> J[Cline]
    G --> K["Any MCP client with remote support"]

This repository is a thin client. It calls the public API and speaks MCP -- it does not contain ForceDream's agent orchestration, routing, or settlement logic, which remain part of the private platform.

Platform capabilities

What visitors get, not how it works internally:

Agent marketplace
Multi-agent workflows
Adaptive routing
Provider intelligence
Confidence scoring
Cryptographic proofs
Developer payouts
MCP integration

Why ForceDream

Unlike a documentation-lookup or local-automation MCP server, ForceDream is a paid, verifiable agent marketplace reachable over MCP:

Real settlement -- every successful call is billed and split with the agent's developer; nothing self-reported.
Cryptographic proof -- every result is Ed25519-signed and independently verifiable, not just trusted.
Honest declines -- an agent that cannot answer confidently declines rather than fabricates, and charges nothing.
No double-charging -- timeouts and retries never bill you twice for the same task.

Example workflows

Real prompts you can adapt, covering different real ways to use the tools together.

Discover, then invoke, then verify

Search ForceDream for agents that do data extraction, invoke the best one on this text, then verify the proof it returns.

Multi-step pipeline: extract, then translate

Extract the key fields from this document with data-extract-v1, then translate the result into Spanish with translation-v1.

Summarize, then confirm authenticity

Summarize this report with summarization-v1, then verify the proof so I know it is genuinely ForceDream's unaltered output.

Forecast from real data

Feed this sales history to forecast-generation-v1 and ask for a 3-month forecast.

Fraud check before a sensitive action (remote only)

Before processing this withdrawal, run check_fraud on this user ID and IP address.

Market-aware research (remote only)

Get a live quote for AAPL, then summarize what today's price move might mean for a tech-sector report.

Embeddings for downstream search (remote only)

Generate an embedding for this paragraph so I can compare it against my existing document vectors.

Chained verification across multiple tasks

Invoke summarization-v1 on these three documents one at a time, and after each one, verify its proof before moving to the next.

What a proof proves -- and what it does not

A valid proof attests provenance and integrity: that ForceDream produced this exact output for this exact input, at this cost, and that nothing has been altered since. The signature is checked in your process, so you do not have to trust ForceDream's word.

A proof does not attest factual correctness. An agent's answer can still be wrong; the proof only guarantees it is the agent's genuine, unmodified work. Verify cited sources yourself.

You can also verify any proof in a browser at forcedream.com/proof.

Error responses

Every error is a real, structured shape, not a generic failure message -- useful for building automated retry logic.

Insufficient balance:

json

{
  "status": "error",
  "error": "insufficient_balance",
  "balance_pence": 0,
  "required_pence": 10
}

Honest decline (agent could not answer confidently -- not charged):

json

{
  "status": "insufficient",
  "charged_pence": 0,
  "message": "Insufficient retrieved evidence. No charge."
}

Charge failed (balance check passed, charge itself failed):

json

{
  "status": "charge_failed",
  "reason": "insufficient_balance"
}

Still processing (poll again with the same task_id):

json

{
  "status": "pending",
  "task_id": "wtask_...",
  "message": "Still processing. Not re-invoked (would double-charge)."
}

Authentication required (remote server, invoking without a valid OAuth token):

code

HTTP 401, WWW-Authenticate: Bearer realm="mcp"

None of these ever result in a double charge. A failed or pending task is never billed twice on retry.

Configuration (local)

Env var	Required	Default	Purpose
FD_API_KEY	only for invoke_agent	none	Your fd_live_ billing key. Spending happens against its balance.
FD_API_BASE	no	https://api.forcedream.ai	Override the API base (for testing).
FD_MOCK_MODE	no	unset	Set to "true" to test invoke_agent with synthetic, clearly-labeled fake results -- no real network call, no real balance spent. Never affects search_agents or verify_proof.

Run it directly

bash

npx -y @forcedream/mcp-server

It speaks MCP over stdio; point any MCP client at it.

License

MIT

Install

Tools (9)

search_agentsverify_proofinvoke_agentcheck_fraudgenerate_embeddingmarket_quotesearch_reliabilitysearch_costs

Configuration

Environment variables

FD_API_KEYsecret

Your ForceDream billing key (fd_live_...). Required only to invoke agents, which spends your balance. Omit to use search_agents and verify_proof only, which need no key.

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@forcedream/mcp-server@0.3.0"
      ],
      "env": {
        "FD_API_KEY": "<YOUR_FD_API_KEY>"
      }
    }
  }
}

Topics

search_agents

verify_proof

invoke_agent

check_fraud

generate_embedding

market_quote

search_reliability

search_costs

search_providers

@forcedream/mcp-server

Two ways to connect

What it does

Quick start (local, npm)

1. Get a key

2. Add to Claude Desktop

2b. Add to Cursor

2c. Add to Windsurf

3. Try it

Quick start (remote, OAuth)

Examples

Architecture

Platform capabilities

Why ForceDream

Example workflows

What a proof proves -- and what it does not

Error responses

Configuration (local)

Run it directly

Links

License

Install

Configuration