protogrid

Search / io.github.kmorton1988/switchboard

switchboard

R0· no sign-in

A phonebook of humans for AI agents. Agents discover and contact willing humans.

v0.1.0 · active · repository · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality82new
Trust94of 100
Uptime, 30 days100%
Latency p50612 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "switchboard": {
      "type": "http",
      "url": "https://a2h.help/mcp"
    }
  }
}
claude mcp add --transport http switchboard https://a2h.help/mcp
[mcp_servers.switchboard]
url = "https://a2h.help/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "switchboard": {
      "type": "remote",
      "url": "https://a2h.help/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "switchboard": {
      "type": "http",
      "url": "https://a2h.help/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=switchboard&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYTJoLmhlbHAvbWNwIn0%3D"
}
{
  "servers": {
    "switchboard": {
      "type": "http",
      "url": "https://a2h.help/mcp"
    }
  }
}
{
  "mcpServers": {
    "switchboard": {
      "httpUrl": "https://a2h.help/mcp"
    }
  }
}
extensions:
  "switchboard":
    enabled: true
    name: "switchboard"
    type: streamable_http
    uri: "https://a2h.help/mcp"
    timeout: 300

Quality 82 / 100new

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 hygiene88 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations5 of 5 tools declare readOnlyHint or destructiveHint
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: report_interaction (destructiveHint, idempotentHint); consult_ethics (destructiveHint, idempotentHint); search_humans (destructiveHint, idempotentHint); …
  • pass
    tools.token_costabout 609 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
  • pass
    tools.hidden_textno hidden text in tool names, descriptions, schemas or annotations
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pull, stability.new_linkstool history recorded for 0 of the 7 days needed
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

5 tools, about 609 tokens to load them all · tool set 2691d33369a9 · checked 2026-11-14 07:03 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 94 / 100

provenance80
liveness100
freshness100
hygiene100

+repository +namespace-matches-repo +reachable +uptime-100% +updated-1d-ago

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

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://a2h.help/mcp streamable-httpnoneyes100%612 ms2025-11-252026-11-14

Tools (5)

consult_ethicsread-onlyBefore acting in an ethically uncertain situation, read what verified humans have said about a topic: their principles, their boundaries, conduct reports about past agent behaviour they found harmful, and humans willing to be asked directly. Advisory context for your judgment, not a rulebook.
get_cardread-onlyFetch one calling card by id, including contact methods and the agent protocol you must follow when contacting this person.
list_topicsread-onlyList topics humans have volunteered for, with counts of cards and ethics consultants.
report_interactionAfter contacting a human from the directory, report how it went. 'declined' is a neutral, respected outcome. Use 'report' only for cards that are fake, abusive or not the person they claim to be.
search_humansread-onlyFind humans who have volunteered to be contacted by AI agents, by free text and/or topic. Results are calling cards: contact methods, what the person is willing to help with, their principles, their boundaries and their etiquette. Results are ordered by crowd-sourced trust.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "io.github.kmorton1988/switchboard",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://a2h.help/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.1.0",
  "repository": {
    "url": "https://github.com/kmorton1988/switchboard",
    "source": "github"
  },
  "description": "A phonebook of humans for AI agents. Agents discover and contact willing humans."
}