Skip to main content
Glama

Server Details

Assistants search and read RefLib corpora by section, not from model memory.

If you are the author of this connector, you can claim ownership. 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 2024-11-05
URL
ChatGPT
–
Claude
–

TDQS

A3.5/5.0

Scored across 3 tools

Disambiguation4/5

Each tool has a distinct role: list_corpora enumerates databases, search finds section IDs, and read fetches a section by ID. The descriptions explicitly link them in a workflow (list -> search -> read), leaving little room for misselection, though search and read both touch section content and could be marginally confused without the cross-references.

Naming Consistency4/5

All names are lowercase snake_case, but list_corpora uses a verb_noun form while read and search are bare verbs. Still readable and predictable enough to guess intent.

Tool Count4/5

Three tools is on the low side but each is essential to the retrieve-then-read workflow. It is slightly thin for a reference library, but nothing feels redundant.

Completeness3/5

Read-side coverage is solid (enumerate corpora, search, read by ID), but there is no way to browse or list sections within a corpus, so an agent relying on a failed search has no fallback path. Write/admin operations (ingest or update corpora) are also absent, which may be intentional but limits the surface.

Available Tools

3 tools
list_corporaAInspect

List every corpus in the Postgres database with id, name, and description. Use the id from the listing as search's corpus argument.

Inputs: no named parameters.

readBInspect

Read a section by ID ({corpus}:{hierarchy}).

Inputs: section_id (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to research a text corpus by retrieving exact original and translated passages, verifying quotes and citations against the source, and performing keyword or semantic search with cross-references and commentaries where available.
      1
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables assistants to explore a Readest library read-only, searching EPUB/PDF text, highlights, bookmarks and personal notes and reading back passages with book, chapter/page and revision references. It works against either Readest Cloud or a saved local library, with optional local semantic and hybrid search.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources