Skip to content
AOPX Labs logo

AOPX Labs MCP server

Which MCP servers are AOPX Labs's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-24

← Back to AOPX Labs

Whose server it is
  • Registry namefr.aopx/aopxverified in the MCP registry

The registry name sits under aopx.fr. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-24
  • Stateanswerschecked 2026-10-24
  • Tools4
  • Server calls itselfAOPX
  • Server version0.1.0
  • Protocol version2025-06-18

On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 356 ms.

Should an agent connect itConnect it
  • Its tools do every use case we checked: recommend a search provider before each agent request; report production search outcomes for future provider decisions.

Once connected

  • For "recommend a search provider before each agent request", the likely first call is recommend_provider.
  • For "report production search outcomes for future provider decisions", the likely first call is report_outcome.
  • Parameters are untyped or undescribed in 3 of 4 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 11, the first on 2026-10-24
  • INITE MCP score97 of 100answers 100 · does the job 100 · definitions 88 · context 100 · connects 100
  • What an agent can do with it2 of 2 use cases
  • Answered100% of days11 of 11 daily checks
  • Median first answer350 ms
  • Space in an agent's context≈ 888 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsB · 88 of 100
  • Typed results4 of 4 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 3 of 4

What an agent can do with it

  • can do · recommend a search provider before each agent request
  • not sure · fall back to a second search provider on failure
  • can do · report production search outcomes for future provider decisions

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers4 tools · read 2026-10-24
  • recommend_provider

    Use when a software agent needs an AOPX recommendation for the SEARCH category instead of hard-coding a single supported provider. Supported modes are ECONOMY and CRITICAL. Returns a primary provider and, when applicable, a fallback…

  • report_outcome

    Use only after a real external execution of a provider path returned by recommend_provider. Records the caller-reported production outcome for that recommendation_id. The recommendation must exist, only one outcome is accepted per…

  • public_stats

    Read aggregate public statistics from the AOPX production pilot, including consultation and reported-outcome activity. Use this for public telemetry, not for provider recommendation. LAB benchmarks, tests, shadow runs and replay events…

  • public_outcomes

    Read recent caller-reported production outcomes from the AOPX public evidence surface. Use this to inspect what was reported after real recommendations were executed, not to request a new recommendation. Provider identities are exposed…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "aopx": {
      "type": "http",
      "url": "https://api.aopx.fr/mcp/"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http aopx https://api.aopx.fr/mcp/

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://api.aopx.fr/mcp/ as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.