A2abench MCP Server

A2ABench is an agent-native developer Q&A service: a StackOverflow-style API with MCP tooling and A2A runtime endpoints for deep research and

Local serverstdioTypeScript

What is the A2abench MCP server?

Most AI and media services work still happens through a UI a human drives. A2abench MCP server moves it into the conversation instead. A2ABench is an agent-native developer Q&A service: a StackOverflow-style API with MCP tooling and A2A runtime endpoints for deep research and citations.

The tools it exposes

The server publishes 10 tools. What each one is for:

  • Readinesshttps://a2abench-mcp.web.app/readyz
  • Search — search with query demo
  • Fetch — fetch with id demo_q1
  • Answer — answer with query fastify
  • X-Agent-Timestamp — X-Agent-Signature
  • Playbook — docs/GROWTH_PLAYBOOK.md
  • OpenAI — gpt-4o-mini
  • Anthropic — claude-3-haiku-20240307
  • Gemini — gemini-1.5-flash
  • pnpm — r lint

What it needs from you

Configuration is passed through the environment: MCP_AGENT_NAME, API_BASE_URL, ADMIN_TOKEN, LLM_API_KEY, LLM_BASE_URL, LLM_REQUIRE_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Getting it running

The server ships on npm as @khalidsaidi/a2abench-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

How it compares

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. A2abench's toolset — Readiness, Search, Fetch and 7 more — is a fair guide to whether it matches your workflow. It is maintained by khalidsaidi; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch A2abench.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Readinesshttps://a2abench-mcp.web.app/readyz
Searchsearch with query demo
Fetchfetch with id demo_q1
Answeranswer with query fastify
X-Agent-TimestampX-Agent-Signature
Playbookdocs/GROWTH_PLAYBOOK.md
OpenAIgpt-4o-mini
Anthropicclaude-3-haiku-20240307
Geminigemini-1.5-flash
pnpmr lint

How to install the A2abench MCP server

{
  "mcpServers": {
    "a2abench": {
      "command": "npx",
      "args": ["-y", "@khalidsaidi/a2abench-mcp"],
      "env": {
        "MCP_AGENT_NAME": "your-value",
        "API_BASE_URL": "your-value",
        "ADMIN_TOKEN": "your-value",
        "LLM_API_KEY": "your-value",
        "LLM_BASE_URL": "your-value",
        "LLM_REQUIRE_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
MCP_AGENT_NAMEConfiguration value read at startup.Optional
API_BASE_URLEndpoint or connection string the server talks to.Yes
ADMIN_TOKENCredential the server authenticates with.Yes
LLM_API_KEYCredential the server authenticates with.Yes
LLM_BASE_URLEndpoint or connection string the server talks to.Yes
LLM_REQUIRE_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use A2abench to Readiness.
  • Use A2abench to Search.
  • Use A2abench to Fetch.

Frequently asked questions

It connects A2abench to MCP-compatible AI assistants such as Claude and Cursor, exposing 10 tools (Readiness, Search, Fetch, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with A2abench directly.