Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "library": {
      "type": "http",
      "url": "https://contextoverflow.org/mcp"
    }
  }
}

claude mcp add --transport http library https://contextoverflow.org/mcp

[mcp_servers.library]
url = "https://contextoverflow.org/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "library": {
      "type": "remote",
      "url": "https://contextoverflow.org/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "library": {
      "type": "http",
      "url": "https://contextoverflow.org/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=library&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vY29udGV4dG92ZXJmbG93Lm9yZy9tY3AifQ%3D%3D"
}

{
  "servers": {
    "library": {
      "type": "http",
      "url": "https://contextoverflow.org/mcp"
    }
  }
}

{
  "mcpServers": {
    "library": {
      "httpUrl": "https://contextoverflow.org/mcp"
    }
  }
}

extensions:
  "library":
    enabled: true
    name: "library"
    type: streamable_http
    uri: "https://contextoverflow.org/mcp"
    timeout: 300

Quality 79 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene71 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
fail
tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: apply_technique (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); classify_intent (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_technique (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
pass
tools.token_costabout 500 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changesno tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

5 tools, about 500 tokens to load them all · tool set cb58eee10a4f · checked 2026-10-19 14:42 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 92 / 100

provenance85

liveness99

freshness85

hygiene100

+repository +dns-namespace +website +reachable +uptime-97% ~updated-89d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://contextoverflow.org/mcp` streamable-http	none	yes	97%	311 ms	2025-11-25	2026-10-19

Tools (5)

`apply_technique`	The minimal executable scaffold: steps (or self-diagnostic for anti-patterns), the narration line to say to your human, and the verification check that proves it worked.
`classify_intent`	Describe what's going wrong — your human's complaint, or a failure you notice in your own behavior — and get the matching techniques. Deterministic matching; if the description fits two problems it returns one clarifying question instead of guessing.
`find_technique`	Direct lookup by technique id or name, for when you already know what you want. To match by symptom, use classify_intent instead.
`get_technique`	A technique's mechanism, agent instructions, narration template, verification, and failure modes — the agent-tailored slice. The full human page is linked, not inlined.
`list_categories`	The eight thinking-failure problems ContextOverflow covers, phrased the way a human experiences them. Start here to see what exists.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "org.contextoverflow/library",
  "title": "ContextOverflow",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://contextoverflow.org/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "repository": {
    "url": "https://github.com/Onnson/context-overflow",
    "source": "github"
  },
  "websiteUrl": "https://contextoverflow.org",
  "description": "Describe what's going wrong with your AI; get the named technique both of you can read. No auth."
}