14803 remote MCP servers · 38 hours of data · last run 2026-09-07 05:25:31
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
| # | Server | Agent readability score | |
|---|---|---|---|
| 1 | france-data | 98/100 | A premier territorial intelligence server offering deep, multi-source French data with expert-level guidance for complex agentic reasoning and tool chaining. |
| 2 | IBANforge | 98/100 | An elite-tier MCP server with exceptional usage guidance, clear tool boundaries, and proactive error prevention for financial data processing. |
| 3 | tls-radar | 98/100 | A highly sophisticated MCP server for SSL/TLS management, featuring exceptional multi-step workflow guidance and proactive error prevention for agents. |
| 4 | Framesail | 97/100 | A highly sophisticated, workflow-oriented toolset that provides explicit guidance for managing a complex, multi-stage AI video production pipeline. |
| 5 | usaspending-mcp-server | 97/100 | A highly sophisticated MCP server providing deep, interconnected access to US federal spending data with exceptional chaining guidance. |
Get notified when your MCP dependencies adopt the 2026-07-28 stateless spec. Leave your email and we will tell you when transition tracking goes live.
Time series of all measurements — for analysis and data delivery.
API documentation (Swagger) ↗Each column is one probe run. The value is not in a single snapshot but in how these columns shift over time.
Transition to the 2026-07-28 stateless spec — share of readable servers speaking modern/dual. 12-month window.
Servers online vs total measured per run — the pulse of the ecosystem.
Points where servers switched protocol era — the pulse of the legacy→modern migration.
Median across probe legs. Measured even for servers returning 401 — availability needs no auth.
Table view of the charts — colour alone never carries meaning.
| Server▲ | Era | Up | p50 ms | Probes | Last probe |
|---|---|---|---|---|---|
| io.github.CSOAI-ORG/agent-prompt-injection-firewall-mcp https://api.meok.ai/v1/a2a/prompt-injection-firewall | Unreachable | 0% 24s 0% · 7g 0% | 4 | 31 | 07.09 02:57 |
| io.github.CSOAI-ORG/agent-delegation-mcp https://api.meok.ai/v1/a2a/delegation | Unreachable | 0% 24s 0% · 7g 0% | 4 | 33 | 07.09 02:57 |
| io.github.CSOAI-ORG/meok-w3c-tdm-rights-mcp https://api.meok.ai/v1/governance/tdm-rights | Unreachable | 0% 24s 0% · 7g 0% | 4 | 31 | 07.09 02:57 |
| io.github.CSOAI-ORG/meok-ap2-mandate-mcp https://api.meok.ai/v1/a2a/ap2-mandate | Unreachable | 0% 24s 0% · 7g 0% | 4 | 32 | 07.09 02:57 |
| io.github.CSOAI-ORG/agent-policy-enforcement-mcp https://api.meok.ai/v1/a2a/policy-enforcement | Unreachable | 0% 24s 0% · 7g 0% | 4 | 32 | 07.09 02:57 |
| io.github.CSOAI-ORG/meok-eu-aia-art-9-rms-mcp https://api.meok.ai/v1/governance/eu-aia-art-9-rms | Unreachable | 0% 24s 0% · 7g 0% | 4 | 32 | 07.09 02:57 |
| io.github.CSOAI-ORG/agent-mcp-router-mcp https://api.meok.ai/v1/a2a/agent-mcp-router | Unreachable | 0% 24s 0% · 7g 0% | 4 | 32 | 07.09 02:57 |
| io.github.CSOAI-ORG/mcp-spec-compliance-mcp https://api.meok.ai/v1/dev/mcp-spec-compliance | Unreachable | 0% 24s 0% · 7g 0% | 4 | 32 | 07.09 02:57 |
| io.github.CSOAI-ORG/meok-mcp-test-mcp https://api.meok.ai/v1/dev/meok-mcp-test | Unreachable | 0% 24s 0% · 7g 0% | 4 | 31 | 07.09 02:57 |
| io.github.CSOAI-ORG/agent-rate-limiter-mcp https://api.meok.ai/v1/a2a/rate-limiter | Unreachable | 0% 24s 0% · 7g 0% | 4 | 31 | 07.09 02:57 |
Drop your URL — your server gets probed in the next run and appears in the directory with a reliability scorecard.
Writing on the MCP ecosystem: reliability, protocol eras, and measurement findings.