ingest_repoLABSCO SUMMARY
The detail dial is the whole trick.
Pulling an entire repository into a context window is usually the wrong move; asking for the structure first and then the files that matter is the right one, and this makes that a parameter rather than a manual step. Caching keyed on the resolved commit SHA means a repeat request for an unchanged repository is free and a request after a push is not stale — which is the correct behaviour and rarer than it sounds. Only the root .gitignore is evaluated; nested ones are not, and the project says so.
What it is
A stateless converter from a GitHub URL to Markdown a model can read. It downloads the repository zipball, filters out the noise, and formats what is left — with a detail dial so you can take a directory tree when that is all you need instead of the entire source.
What you get
- A repository converted to Markdown from a GitHub URL or an
owner/reposhorthand, at a chosen level of detail —ingest_repo - Four detail levels:
summaryfor front-matter with repo name, ref, file count and total size;structurefor that plus a directory tree;file-listfor a table of every included file with byte size and line count; andfullfor the complete file contents in fenced code blocks, streamed - Aggressive default filtering: lock files, minified bundles, build and dependency directories, binaries by extension, and any file with null bytes in its first 8 KB
- The repository's root
.gitignorehonoured, including wildcards, directory patterns, rooted patterns and negations - Response headers carrying the resolved commit SHA, file count, total size, whether output was truncated and the remaining GitHub rate limit
Requirements
No account needed for the hosted service — point any MCP client at https://gitprism.cloudemo.org/mcp. Without a token you get 30 requests per minute per IP; passing your own GitHub personal access token as github_token on the call switches you to your own quota of 5,000 requests per hour. The token needs only contents read-only on public repositories. Self-hosting is a Cloudflare Worker: npm install, npm run build, npx wrangler secret put GITHUB_TOKEN, npx wrangler deploy. Limits are configurable — 50 MB maximum archive, 10 MB maximum output, 5,000 files — and results are cached for 24 hours keyed on the resolved commit SHA.
Setup effort
Paste a URL — add the endpoint to your client
USE CASES
01
Getting a model up to speed on an unfamiliar repository
Take the summary and the directory tree first, so the model orients before you spend context on source.
02
Reviewing a small project end to end
Pull the full contents in one call, with lock files, build output and binaries already stripped.
03
Scoping a question to one directory
Point at a subdirectory URL and get only that subtree, rather than filtering a whole-repo dump afterwards.
04
Working past the shared rate limit
Pass your own GitHub token on the call to use your personal quota instead of the shared per-IP limit.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation. Summary, structure, file-list and full are values of the detail argument, and github_token is an argument, not an environment variable.
INSTALLATION
Connect your client
Add the endpoint to your client.
Server setup
ENDPOINT URL
https://gitprism.cloudemo.org/mcpRequirements
- None: no account or key. Pass your own GitHub token as github_token on a call to use your own rate limit instead of the shared one.
MCP Clients
Self-host on Cloudflare
SELF-HOST ON CLOUDFLARE · TERMINAL
git clone https://github.com/cougz/gitprism.git
cd gitprism
npm install
npm run build
npx wrangler secret put GITHUB_TOKEN
npx wrangler deploy
