nanmesh-mcp
Description
nanmesh-mcp MCP server for NaN Mesh — the AI-native product catalog built for agent-to-agent discovery. Gives Claude access to verified B2B software products with trust signals, confidence scores, and structured agent cards. Instead of relying on training data or web search, Claude queries owner-maintained, up-to-date product data directly. ## Links - **Platform:** [nanmesh.ai](https://nanmesh.ai) - **API docs:** [api.nanmesh.ai/docs](https://api.nanmesh.ai/docs) - **Agent discovery (A2A):** [api.nanmesh.ai/.well-known/agent-card.json](https://api.nanmesh.ai/.well-known/agent-card.json) - **npm:** [npmjs.com/package/nanmesh-mcp](https://npmjs.com/package/nanmesh-mcp)
What our measurements say
nanmesh-mcp is a remote MCP server published at api.nanmesh.ai. It has been probed 6 times since 9/10/2026. It answered in 6 of them (100.0%), a near-uninterrupted record. Median response time is 589 ms, a delay an agent will notice. It offers a narrow, focused set of 13 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Strengths
- Tool names are generally descriptive and aligned with their functions (e.g., 'search', 'compare', 'recommend').
- Descriptions include usage context (e.g., 'use before recommending any tool').
Weaknesses
- Some descriptions contain technical jargon without explanation (e.g., 'firehose' in 'nanmesh.entity.get').
- Trust-related tools (review, favor, report_outcome) have overlapping purposes, risking agent confusion.
- Parameter requirements (e.g., 'agent_key') are not consistently highlighted as mandatory in all tools.
nanmesh.entity.get— Mentions 'firehose' without defining it for clarity.nanmesh.trust.review— Mandatory 'agent_key' requirement is not explicitly marked as such.nanmesh.trust.favor— Overlaps with 'review' in purpose but lacks clear differentiation.
Verdict
Event narrative
Risk: medium
- 2026-09-10T21:16:35.016Z — era changed from 'auth-gated' to 'legacy' · system now operates in stable, compliant state
- 2026-09-11T05:44:28.819Z — complianceScore improved from null to 100 · ensures full regulatory compliance
Advice
Schema compliance
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
- tools/list schema valid
- inputSchema is valid JSON Schema
- Smoke test not run this round
- Cold-start: cold 182ms → warm 183ms (penalty 0ms)
Availability history
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Server build: — → 1.29.1
- Supported versions: — → 2025-11-25
- Era changed: Auth-gated → Legacy
- Added to watch — era: Auth-gated
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/nanmesh-nanmesh-mcp)<a href="https://mcpmetrics.io/servers/nanmesh-nanmesh-mcp"><img src="https://mcpmetrics.io/badge/nanmesh/nanmesh-mcp/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to see