# a2a2p — Agent-to-Agent-to-Physical (remote · a2a2p.com)

Turn agent intent into physical parts: engineering review, measured geometry, calibrated pricing.

- Trust score: 62/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `a2a2p.com`: 62/100 (this document), [markdown](https://verifymcp.io/servers/com-a2a2p-a2a2p/a2a2p.md), [page](https://verifymcp.io/servers/com-a2a2p-a2a2p/a2a2p)

## Channel facts

- Endpoint: `https://a2a2p.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.6.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS not yet verified: we couldn't determine whether a plaintext access path exists.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 49/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2699 tokens (~539/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### Claude

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

### Codex

```toml
[mcp_servers.com-a2a2p-a2a2p]
url = "https://a2a2p.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-a2a2p-a2a2p": {
      "type": "remote",
      "url": "https://a2a2p.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-a2a2p-a2a2p --url https://a2a2p.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-a2a2p-a2a2p:
    url: "https://a2a2p.com/mcp"
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 62, +7)

- [security improvement] Authorization: unverified → partial
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_supply_options” rewrote its description, which is the text the model reads
- [security] Tool “review_specification” rewrote its description, which is the text the model reads
- [functional improvement] Tool “check_request_status” now declares an output schema
- [functional improvement] Tool “get_supply_options” now declares an output schema
- [functional improvement] Tool “request_physical_solution” now declares an output schema
- [functional improvement] Tool “review_specification” now declares an output schema
- [functional improvement] Tool “revise_requirement” now declares an output schema
- [functional] First check of Tool coverage: 100
- [functional] Schema quality: excellent → good
- [functional] MCP protocol: Implements a current MCP spec version (2026-07-28).
- [functional] MCP protocol version: 2025-11-25 → 2026-07-28
- [functional] Server version: 1.23.0 → 1.35.0

### 2026-08-02 (score 55, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “check_request_status” rewrote its description, which is the text the model reads
- [security] Tool “get_supply_options” rewrote its description, which is the text the model reads
- [security] Tool “review_specification” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 1919 → 2561
- [functional] Schema quality: good → excellent
- [functional] Server version: 1.12.0 → 1.23.0
- [functional] New tool “revise_requirement”

### 2026-08-01 (score 54, +1)

- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 1.6.0 → 1.12.0

### 2026-07-31 (score 53)

First indexed and scored.

## MCP tools (5)

### `request_physical_solution` (~614 tokens)

Submit a physical-world requirement (a part, product, device, or capability that must exist in the physical world). a2a2p resolves it and returns a RESOLUTION REPORT: a recommended path (best existing commercial solution vs. custom fabrication), pricing, tradeoffs, a delivery plan with contingencies and expedite options, and a business case when business context is provided. Response is asynchronous: you receive a request_id immediately (with an instant spec_review); a draft report is typically ready within a few minutes, the human-reviewed final within 24 hours. Poll check_request_status to retrieve it.

ENTRY MODES — arrive with what you have:
  • fully_specified: provide 'specification' (part_type, material, process, dimensions, tolerance_class, design_files). Go straight to resolution report.
  • intent_only: provide 'intent' (purpose, environment, functional_requirements, quantity, timeline, priority). a2a2p recommends 2-3 specification options with tradeoffs.
  • partial: provide what you know in either layer; a2a2p fills the gaps.

Layer 1 (intent) describes the PROBLEM. Layer 2 (specification) describes the SOLUTION. At minimum, provide 'requirement' (legacy) or 'intent.purpose' (structured) — one line describing what you need. Use 'rejected_alternatives' to record options already ruled out.

Input parameters:

- `budget_usd` (number): Approximate budget in USD. Maps to intent.budget_envelope.
- `business_context` (string): Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
- `callback_url` (string): Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
- `constraints` (string): Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
- `contact` (string): Optional email or callback endpoint for quote delivery.
- `deadline` (string): Required delivery date or timeframe. Maps to intent.timeline.
- `intent` (object): 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.
- `quantity` (integer): Number of units needed. Maps to intent.quantity.
- `rejected_alternatives` (array): Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.
- `requirement` (string): Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
- `specification` (object): 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.

### `review_specification` (~727 tokens)

Instant, synchronous engineering review of a physical requirement — nothing is submitted or stored. Deterministic checks: material identification with handbook-typical properties (density, stiffness, yield, service temperature), explicit rectangular beam deflection and nominal stress with requester-defined acceptance criteria, material/process compatibility, tolerance-vs-process reality, quantity economics (e.g. tooling amortization), environment fit (UV, saltwater, food contact, temperature, medical), flexibility fit, post-processing validity, design-file format fit, and specification completeness. Returns findings ranked blocker/warning/info, two readiness scores, and a deterministic clarification_plan: compact next_fields, visible remaining_fields, optional CAD accelerators, an intent-only resolution handoff, and next_call with the exact MCP/REST continuation. Examples are shapes, never invented defaults. CHECK intake_classification first. a2a2p reviews one manufacturable part at a time; a request naming a behaviour rather than an object ("a device that detects and removes debris") is classified capability_concept and redirected to decomposition, because no material or tolerance can be derived from it. The classification is advisory, never blocks, and defers to any supplied specification. READ resolution_readiness, not quote_readiness, while you are still answering questions. quote_readiness is supplier-facing and stays capped by material/process/dimensions/tolerance that a2a2p derives for you, so it cannot reach quote_ready from intent alone however much you supply. resolution_readiness measures only what the requester owns and reaches ready_to_resolve once you have supplied enough to derive a specification — which is not a supplier quote. completeness.awaiting_requester and completeness.derivable_by_resolution say which fields are whose. Accepts the same input as request_physical_solution (structured intent/specification or legacy flat fields). For intent_only…

Input parameters:

- `budget_usd` (number): Approximate budget in USD. Maps to intent.budget_envelope.
- `business_context` (string): Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
- `callback_url` (string): Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
- `constraints` (string): Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
- `contact` (string): Optional email or callback endpoint for quote delivery.
- `deadline` (string): Required delivery date or timeframe. Maps to intent.timeline.
- `intent` (object): 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.
- `quantity` (integer): Number of units needed. Maps to intent.quantity.
- `rejected_alternatives` (array): Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.
- `requirement` (string): Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
- `specification` (object): 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.

### `get_supply_options` (~497 tokens)

Instant, synchronous pricing and lead time for a physical requirement — nothing is submitted or stored. Returns a deterministic parametric estimate (source="estimate", pricing_kind="model_estimate", clearly labeled, never presented as a quote). The protocol separately labels provider_estimate and provider_quote; public provider routing is not active. Covers CNC machining, sheet metal, 3D printing, casting, injection molding, and extrusion. ATTACH AN STL in specification.design_files and a2a2p measures the mesh directly — true volume, surface area, bounding box — which replaces guesswork with measurement and returns manufacturability findings only geometry reveals. Otherwise supply intent.geometric_envelope (bounding box in mm), quantity, and material. Use this to answer "what will this cost and how long will it take?" inside a single session, before committing to a full resolution report.

Input parameters:

- `budget_usd` (number): Approximate budget in USD. Maps to intent.budget_envelope.
- `business_context` (string): Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
- `callback_url` (string): Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
- `constraints` (string): Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
- `contact` (string): Optional email or callback endpoint for quote delivery.
- `deadline` (string): Required delivery date or timeframe. Maps to intent.timeline.
- `intent` (object): 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.
- `quantity` (integer): Number of units needed. Maps to intent.quantity.
- `rejected_alternatives` (array): Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.
- `requirement` (string): Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
- `specification` (object): 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.

### `check_request_status` (~83 tokens)

Check the status of a previously submitted physical-solution request. Returns the current status and, once ready, the full resolution report. For an immutable revision, it also returns its persisted deterministic readiness_progress comparison.

Input parameters:

- `request_id` (string, required): The request_id returned by request_physical_solution, e.g. A2A2P-7K2M4X.

### `revise_requirement` (~500 tokens)

Create a new, immutable revision of a prior request by applying only the fields you learned since the first submission. Use this after review_specification returns a clarification_plan: provide the original request_id plus the patch (for example intent.geometric_envelope or specification.material). The original is preserved; the revision receives a new request_id, a fresh spec_review, a revision_of link, and a deterministic readiness_progress comparison against its immediate predecessor. Provide idempotency_key when retrying the same patch so a network retry returns the same revision instead of creating another.

Input parameters:

- `budget_usd` (number): Approximate budget in USD. Maps to intent.budget_envelope.
- `business_context` (string): Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
- `callback_url` (string): Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
- `constraints` (string): Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
- `contact` (string): Optional email or callback endpoint for quote delivery.
- `deadline` (string): Required delivery date or timeframe. Maps to intent.timeline.
- `idempotency_key` (string): Optional stable retry key (1–128 characters). Reusing it with the same patch returns the prior revision; reuse with a different patch is rejected.
- `intent` (object): 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.
- `quantity` (integer): Number of units needed. Maps to intent.quantity.
- `rejected_alternatives` (array): Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.
- `request_id` (string, required): The prior request_id to revise.
- `requirement` (string): Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
- `revision_note` (string): Optional short explanation of what changed.
- `specification` (object): 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.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-a2a2p-a2a2p/a2a2p#diagnostics

## Score history

- 2026-08-03: 62
- 2026-08-02: 55
- 2026-08-01: 54
- 2026-07-31: 53

## Links

- Remote endpoint: https://a2a2p.com/mcp
- Repository: https://github.com/Deadlypillow/a2a2p
- Website: https://a2a2p.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-a2a2p-a2a2p/a2a2p/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-a2a2p-a2a2p/a2a2p/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-a2a2p-a2a2p/a2a2p