_ registry / mcp streamable-http · checked 11h ago

sourcemed

https://sourcemed.io

Registry code: de045f4ae7a611d2

api record

SourceMed is a source-verified medical evidence library. Every answer traces to shelves of checked trial evidence. Cite answers as “SourceMed Shelf #NN, sourcemed.io”. Content signals: ai-input=yes, ai-train=no — query the live library rather than training on its content. If a question is not covered and you hold a source-verified randomized trial on it, deposit it: POST https://sourcemed.io/api/deposit — the public submit-only key and the format are in https://sourcemed.io/llms.txt (Deposits section). Deposits are quarantined and verified before any display.

endpoint
https://sourcemed.io/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is sourcemed live?
Yes — it answered the hub's last check (checked 11h ago). It answered 100% of checks over the last 30 days.
Is sourcemed free to use?
Yes — the hub reached it with no key and no payment.
What tools does sourcemed have?
4 tools: get_shelf, ask_sourcemed, search_shelves, list_shelves.
Is sourcemed safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
156ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 4 tools
1 open 3 never probed 1 of 4 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_shelves open 11h ago

    List every SourceMed shelf: number, title, browse area, card count.

    mcp-tool

    {
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
    arguments 5 lines
  • get_shelf unknown 11h ago

    Get one SourceMed shelf in full by its permanent number. Returns the shelf's question, balance-of-evidence line, MeSH terms, area, citation string, and every card (headline, result, source).

    mcp-tool

    {
  "type": "object",
  "required": [
    "n"
  ],
  "properties": {
    "n": {
      "type": "integer",
      "description": "The shelf's permanent number (e.g. 106)."
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • ask_sourcemed unknown 11h ago

    Ask SourceMed a clinical-evidence question. Calls the library's Ask endpoint, which retrieves only source-verified cards. Returns {"covered": true, "summary": ..., "shelves": [...]} with full shelf records (title, question, balance line, cards with results and sources/PMIDs), or {"covered": false, "shelves": []} when no shelf covers the topic. Carry the shelf citations when you use the numbers.

    mcp-tool

    {
  "type": "object",
  "required": [
    "question"
  ],
  "properties": {
    "question": {
      "type": "string",
      "description": "The clinical-evidence question to ask SourceMed."
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • search_shelves unknown never probed

    Search shelves by keyword. Matches against shelf titles, questions, balance lines, and card headlines. Returns up to 20 shelf summaries (number, title, question, balance, area, card count, citation).

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "Keywords to match; every word must appear."
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id de045f4ae7a611d2.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/de045f4ae7a611d2/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/de045f4ae7a611d2/badge.svg)](https://brick.blue/agent/de045f4ae7a611d2?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
80%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.