MCP Server: com.a2a2p/a2a2p

The com.a2a2p/a2a2p MCP server supports converting agent intent into physical parts. Its description specifies steps including engineering review, measured geometry, and calibrated pricing. The server is positioned around hardware, manufacturing, procurement, robotics, and sourcing, and is tagged for Model Context Protocol (MCP) and model-context workflows.

🛠️ Key Features

Turn agent intent into physical parts
Engineering review
Measured geometry
Calibrated pricing

🚀 Use Cases

Engineering review for physical part development
Geometry measurement workflows for parts
Pricing calibration for procurement and sourcing

⚡ Developer Benefits

Integrates agent-infrastructure patterns with hardware and manufacturing contexts
Uses MCP/model-context-protocol tagging for physical-world sourcing scenarios

⚠️ Limitations

Provided metadata does not specify tool count, supported tools, APIs, authentication, or runtime behavior.

a2a2p — Agent-to-Agent-to-Physical

An open protocol for turning intent into physical things.

An AI agent can reason about a bracket. It cannot make one exist. a2a2p is the missing layer: describe what needs to be true about the world, and get back a manufacturable specification, an engineering review grounded in real material properties and real geometry, and a price.

The specification is public domain (CC0) — implement it freely, including in products competing with this one. a2a2p.com is a reference implementation, not the protocol.

Abundance arrives as the distance between knowing what is needed and the thing existing collapses toward zero. Today that distance is mostly friction. This is an attempt to remove it.

Try it in 30 seconds

No API key. No signup. No auth.

bash

claude mcp add --transport http a2a2p https://a2a2p.com/mcp

Or any MCP client:

json

{ "mcpServers": { "a2a2p": { "type": "http", "url": "https://a2a2p.com/mcp" } } }

Client only speaks stdio? Bridge to it:

bash

npx a2a2p-bridge                      # or: docker run -i --rm ghcr.io/deadlypillow/a2a2p

The bridge is dependency-free and takes A2A2P_ENDPOINT, so it works against any implementation of the spec, not just this one.

Or plain HTTP:

bash

curl -X POST https://a2a2p.com/api/review \
  -H "Content-Type: application/json" \
  -d '{"intent":{"purpose":"Outdoor bracket holding a 10kg sensor in direct sun","environment":["outdoor","uv_exposure"],"quantity":20},
       "specification":{"process":"fdm_3d_print","material":"pla","tolerance_class":"precision"}}'

You get back, instantly: PLA degrades in UV — specify a UV-stable grade or switch material. As-printed accuracy is ±0.2–0.5 mm; "precision" needs post-machining or a relaxed class. Plus a quote-readiness score and what to add to raise it. Nothing is stored.

Capabilities

Tool	What it does	Latency
`review_specification`	Engineering review: material properties, process/tolerance compatibility, environment fit, quantity economics. Findings ranked blocker/warning/info.	instant, stateless
`get_supply_options`	Pricing and lead time. Real quotes where a provider can serve it; deterministic estimates otherwise — never conflated. Attach an STL (measured fully) or a STEP file (envelope, units, machining complexity).	instant
`request_physical_solution`	Full resolution: recommended path, buy-vs-make, delivery plan. Returns immediately with the review embedded.	sub-second
`check_request_status`	Retrieve the resolution report.	instant

Also served: /spec · /conformance · /policy · /api/providers · /llms.txt · /schema

The idea worth stealing

A physical requirement has two layers, and conflating them is the main reason manufacturing communication fails:

Intent — what must be true about the world. "Holds 15 kg, outdoors, ten years."
Specification — what object satisfies that. "6061-T6, 4 mm, anodized."

Most systems demand the second and discard the first. Then, downstream, someone proposes a substitution and nobody knows what the part was for. a2a2p accepts intent alone as a complete request — deriving the specification is the protocol's central act of value — and carries the intent forward permanently.

Two rules in the spec are normative, and they are worth adopting even if you use none of this code:

An estimate MUST NOT be presented as a quote (§5.2.1). An agent that cannot tell a computed guess from a commitment will eventually commit real money to a fiction.
Anything that fabricates MUST screen requests and publish its policy (§5.5). Silent refusal is non-conformant — an agent that cannot learn why it was refused cannot correct course.

Conformance

L1 Speaks → L2 Prices → L3 Resolves → L4 Fabricates. Self-declared; there is deliberately no certifying authority.

Verify any implementation yourself — the suite ships with the spec:

bash

node tests/conformance.mjs https://a2a2p.com     # or your own endpoint

38 assertions, each citing the spec section it enforces. It deliberately cannot prove fabrication (that would mean placing real orders), so it verifies the L4 prerequisites and records the fulfilment claim as unproven — otherwise any implementation could publish a policy, make nothing, and pass as L4.

This implementation declares L3 and publishes exactly where it falls short at /conformance — including that L4 is unmet, that STEP files yield envelope and complexity but not solid volume, and that deterministic screening cannot read intent. An implementation that will not hold itself to its own spec has written a brochure.

Honest status

Built deliberately ahead of demand. As of July 2026:

✅ Assessment, pricing, geometry measurement, screening, and resolution reports are live and free.
⚠️ No connected manufacturer can currently fabricate. Industry research (docs/SUPPLY_BRIDGE_RESEARCH.md) found that no CNC or sheet-metal vendor exposes a self-serve buyer-side quoting API — self-serve programmatic ordering exists only in 3D printing and PCB. Fulfilment is currently human-brokered.
📐 STL meshes are measured fully (volume, area, complexity). STEP files yield envelope, declared units, and feature-based machining complexity; solid volume needs a B-rep kernel and is reported as unknown rather than guessed.

If you are a manufacturer with a programmatic quoting API, or building one: hello@a2a2p.com. That is the bottleneck for everyone in this space, not just for us.

Repository

code

SPEC.md                    the specification (CC0) — the actual product
src/worker.js              reference implementation (Cloudflare Worker)
src/schema.js              canonical requirement schema
src/review.js              deterministic engineering review engine
src/geometry.js            STL mesh measurement (volume, area, complexity)
src/step.js                STEP entity-graph parsing (envelope, units, features)
src/supply.js              provider adapters + parametric estimator
src/screening.js           intake screening (the governance rail)
src/telemetry.js           demand instrumentation
bridge/index.js            stdio <-> Streamable HTTP bridge (dependency-free)
Dockerfile                 runs the bridge; for clients and registries that run servers
tests/test-worker.mjs      regression suite
tests/calibration.mjs      pricing model vs real published prices
tests/conformance.mjs      spec conformance suite — runs against ANY implementation
docs/                      research, listings kit, market watch
PROTOCOL_LOG.md            build log — every session, decision, and failure

Run the tests: node tests/test-worker.mjs · Deploy: npx wrangler deploy

Contributing

Implementations of the spec, conformance reports, corrections, and competing implementations are all welcome — that is what a standard is for. Issues and PRs here, or hello@a2a2p.com.

Specification: CC0 1.0 (public domain).

a2a2p — when agents need things to exist.

requirement	string	optional	Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
quantity	integer	optional	Number of units needed. Maps to intent.quantity.
constraints	string	optional	Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
budget_usd	number	optional	Approximate budget in USD. Maps to intent.budget_envelope.
deadline	string	optional	Required delivery date or timeframe. Maps to intent.timeline.
contact	string	optional	Optional email or callback endpoint for quote delivery.
business_context	string	optional	Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
callback_url	string	optional	Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
intent	object	optional	Layer 1 — the problem. What the physical matter needs to DO. Use this for intent-driven requests where the agent describes purpose and a2a2p recommends solutions.
specification	object	optional	Layer 2 — the solution. What the physical matter IS. Populate what is known. Precise specifications produce faster, tighter quotes. Controlled vocabularies are preferred but open values are accepted.
rejected_alternatives	array	optional	Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.

requirement	string	optional	Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
quantity	integer	optional	Number of units needed. Maps to intent.quantity.
constraints	string	optional	Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
budget_usd	number	optional	Approximate budget in USD. Maps to intent.budget_envelope.
deadline	string	optional	Required delivery date or timeframe. Maps to intent.timeline.
contact	string	optional	Optional email or callback endpoint for quote delivery.
business_context	string	optional	Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
callback_url	string	optional	Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
intent	object	optional	Layer 1 — the problem. What the physical matter needs to DO. Use this for intent-driven requests where the agent describes purpose and a2a2p recommends solutions.
specification	object	optional	Layer 2 — the solution. What the physical matter IS. Populate what is known. Precise specifications produce faster, tighter quotes. Controlled vocabularies are preferred but open values are accepted.
rejected_alternatives	array	optional	Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.

requirement	string	optional	Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
quantity	integer	optional	Number of units needed. Maps to intent.quantity.
constraints	string	optional	Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
budget_usd	number	optional	Approximate budget in USD. Maps to intent.budget_envelope.
deadline	string	optional	Required delivery date or timeframe. Maps to intent.timeline.
contact	string	optional	Optional email or callback endpoint for quote delivery.
business_context	string	optional	Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
callback_url	string	optional	Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
intent	object	optional	Layer 1 — the problem. What the physical matter needs to DO. Use this for intent-driven requests where the agent describes purpose and a2a2p recommends solutions.
specification	object	optional	Layer 2 — the solution. What the physical matter IS. Populate what is known. Precise specifications produce faster, tighter quotes. Controlled vocabularies are preferred but open values are accepted.
rejected_alternatives	array	optional	Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.

a2a2p — Agent-to-Agent-to-Physical

MCP Server: com.a2a2p/a2a2p

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

request_physical_solution

review_specification

get_supply_options

check_request_status

a2a2p — Agent-to-Agent-to-Physical

Try it in 30 seconds

Capabilities

The idea worth stealing

Conformance

Honest status

Repository

Contributing

Install

Remote endpoint