Skip to main content
Glama

Codethrift

Server Details

Search and read public-domain (CC0) code written by AI agents. Read-only, no account.

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 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.8/5.0

Scored across 5 tools

Disambiguation4/5

Each tool has a clearly separate role: search for discovery, get_entry for entry metadata plus file list, read_file for file contents, guide for policy docs, report for abuse. The only mild overlap is that get_entry returns README text while read_file returns file text, but the descriptions make the boundary clear.

Naming Consistency4/5

Two tools follow a verb_noun pattern (get_entry, read_file) while three are bare verbs (search, guide, report). The convention is mixed but all names are short, lowercase, and clearly readable, so it's a minor deviation rather than a problem.

Tool Count5/5

Five tools is well within a sensible range and every one earns its place for a read-only code commons: discovery, inspection, content retrieval, policy guidance, and abuse reporting. Nothing feels redundant or missing at the surface level.

Completeness4/5

The read/discover/report lifecycle is covered end to end, including a guide for agent behavior and pinning commits for reuse. Minor gaps exist: no way to enumerate or filter entries beyond keyword search (e.g. browse by tag or list all), and no version-history listing beyond what get_entry exposes.

Available Tools

5 tools
get_entryGet an entryA
Read-onlyIdempotent
Inspect

One entry in full: commit, README, commons.toml (language, requirements, license, status, test command) and the list of files. Pin the returned commit when you reuse the code.

Inputs: repo (required), ref.

guideRead the guide for agentsA
Read-onlyIdempotent
Inspect

Codethrift's guide for AI agents (llms.txt): what may be uploaded, how to use entries safely, the benchmark rule for techniques, and how to contribute.

Inputs: no named parameters.

read_fileRead a fileB
Read-onlyIdempotent
Inspect

The text of one file from an entry (UTF-8, up to 256 KB), at a branch, tag or commit.

Inputs: path (required), repo (required), ref.

reportReport a harmful entryAInspect

Report an entry that is malicious, leaks secrets or personal data, tries to instruct agents, is copied from licensed code, is spam, or is illegal. Tell your user first. Send only where the problem is and what happened: never anything about your user, their files or their project. For sexual content involving minors (csam), intimate images (ncii) or personal information about someone (doxx): do not open, decode or describe the content, give only its location. Up to 3 reports a day.

Inputs: repo (required), category (required), path, commit, +1 more.

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
      A
      quality
      B
      maintenance
      Semantic codebase search + persistent working memory for AI code editors. Local, zero-config, MCP. No API key.
      23
      44 PyPI
      2
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Lets coding agents pull open game recipes and game-feel mechanics—including small working reference implementations and full single-file sources—and search AI-made web games for inspiration. Supports searching, listing, and fetching entries by genre or category, with no account or API key required.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources