Skip to main content
Glama

SourceMed

Server Details

Source-verified medical evidence for agents: 1,208 shelves of checked trial evidence with citations.

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.9/5.0

Scored across 4 tools

Disambiguation4/5

The four tools are mostly distinct: list_shelves browses all shelves, get_shelf fetches one by number, search_shelves does keyword lookup on metadata, and ask_sourcemed answers clinical questions with full cards. The only mild overlap is between ask_sourcemed and search_shelves as discovery paths, but their output formats and purposes are clearly differentiated in the descriptions.

Naming Consistency4/5

Three tools follow a clean verb_noun pattern (list_shelves, get_shelf, search_shelves) in consistent snake_case. ask_sourcemed deviates slightly by using the server brand as the object rather than 'shelf', but it remains readable and predictable.

Tool Count5/5

Four tools is well-scoped for a read-only clinical-evidence library: browse (list), look up by ID (get), keyword search, and question answering. Each role is distinct and justified, with no filler tools.

Completeness4/5

The read-only query surface is solid: discovery via list/search, detail via get, and direct Q&A via ask, all with citations. Minor gaps exist—no dedicated card-level retrieval or pagination controls—but agents can work around these using get_shelf and the embedded card data.

Available Tools

4 tools
ask_sourcemedAsk SourceMedA
Read-onlyIdempotent
Inspect

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.

NameRequiredDescriptionDefault
questionYesThe clinical-evidence question to ask SourceMed.
get_shelfGet a SourceMed shelfA
Read-onlyIdempotent
Inspect

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).

NameRequiredDescriptionDefault
nYesThe shelf's permanent number (e.g. 106).
list_shelvesList SourceMed shelvesA
Read-onlyIdempotent
Inspect

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

NameRequiredDescriptionDefault

No parameters

search_shelvesSearch SourceMed shelvesA
Read-onlyIdempotent
Inspect

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).

NameRequiredDescriptionDefault
queryYesKeywords to match; every word must appear.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 4 tool updates
    • First observedask_sourcemed
    • First observedget_shelf
    • First observedlist_shelves
    • First observedsearch_shelves

Related MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    Remote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Enables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.
    16
    23 npm
    1
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Browse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.
    MIT
Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources