MCP serverio.github.vanshulgoyal101/ctx
Turn a GitHub repo or docs site into agent-ready context: pack it or search it, over MCP.
Overview
Score?
UNRATED 0.793
of what a free look can see, on 32 looks
Looks
35
last 12 hr ago
Tools
6
More info
URL
ctx.vanshul.com/mcp
streamable-http
Says it is
vanshul-ctx 1.0.0
protocol 2025-06-18
In the record since
32 days ago
Among servers18,413 with a card
0median 0.606 · this server 0.793 · highest on record 0.8561
Toolsfrom sha256:b2f451b487…7e61c0
| Tool | Schema |
|---|---|
| get_file Return the full text of a single file in a repository, by path. Use after list_files or search_context to drill in. |
input · no output |
| list_files List the text files ctx would include for a repository (after stripping binaries, lockfiles and build dirs), with their byte sizes. Cheap way for an agent to see the layout before |
input · no output |
| pack_docs Crawl a documentation site from a start URL and return it as one agent-ready context blob: each page extracted to clean Markdown, concatenated with its URL. Stays within the same s |
input · no output |
| pack_repo Fetch a GitHub repository and return it as one agent-ready context blob: text files concatenated with clear "==== path ====" headers, binaries/lockfiles/build dirs stripped, with a |
input · no output |
| search_context Search a GitHub repository and return only the passages that match a query — each with its file path, line number and a relevance score. Far more token-efficient than pack_repo whe |
input · no output |
| search_docs Crawl a documentation site and return only the passages that match a query — each with its page URL, line and a relevance score. Token-efficient way to answer a question from docs |
input · no output |
Verify it yourself
npx teppi-check https://ctx.vanshul.com/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ2NPYAKRN0BDMSHA6BF45