ctx MCP

A public, agent-first MCP server that converts GitHub repositories or documentation sites into token-efficient context. It allows AI agents to pack entire codebases or doc sites into single blobs or perform ranked searches to retrieve only relevant passages, files, and lines, supporting tools like pack_repo, search_context, list_files, get_file, pack_docs, and search_docs.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by Vanshul

MCP endpoint (Streamable HTTP)

https://ctx.vanshul.com/mcp

Vendor documentation

What its tools do

6 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (6)

pack_repo
search_context
list_files
get_file
pack_docs
search_docs

6 of 6 have a description · 0 of 6 declare behavior hints · 6 of 6 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 7, 2026, 3:42 AM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Pack a whole GitHub repository into a single token-counted context blob for an AI agent.
Search a repository for specific passages, returning relevant files, lines, and scores.
Crawl a documentation site and return clean Markdown as a concatenated context blob.
Search a documentation site for specific queries to find relevant pages and passages.

Source and maintenance

Community listingRegistry 1.0.0

mcp-registry: io.github.vanshulgoyal101/ctx@1.0.0 Source repository Project website

Maintenance checked: Nov 7, 2026, 12:20 AM UTC

Protocol and capabilities

Server: vanshul-ctx 1.0.0
MCP protocol negotiated in check: 2025-06-18
Tools: 6 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Tools to turn a GitHub repo into agent-ready context. Pass a repo as "owner/repo" or a github.com URL.

Tools

6 advertised

pack_repo

Advertised by the server during the last successful anonymous check.

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 token estimate. Use include/exclude globs to focus, and max_tokens to fit a budget.

pack_repo input schema

{
  "type": "object",
  "required": [
    "repo"
  ],
  "properties": {
    "ref": {
      "type": "string",
      "description": "Optional branch, tag or commit SHA (defaults to the default branch)."
    },
    "repo": {
      "type": "string",
      "description": "A GitHub repo as \"owner/repo\" or a github.com URL."
    },
    "exclude": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional glob patterns (support **, *, ?)."
    },
    "include": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional glob patterns (support **, *, ?)."
    },
    "max_tokens": {
      "type": "number",
      "description": "Stop adding files once the estimate exceeds this many tokens."
    }
  }
}

search_context

Advertised by the server during the last successful anonymous check.

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 when you need a specific detail (e.g. "where is auth handled?").

search_context input schema

{
  "type": "object",
  "required": [
    "repo",
    "query"
  ],
  "properties": {
    "ref": {
      "type": "string",
      "description": "Optional branch, tag or commit SHA (defaults to the default branch)."
    },
    "repo": {
      "type": "string",
      "description": "A GitHub repo as \"owner/repo\" or a github.com URL."
    },
    "query": {
      "type": "string",
      "description": "Space-separated search terms; matching is case-insensitive."
    },
    "exclude": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional glob patterns (support **, *, ?)."
    },
    "include": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional glob patterns (support **, *, ?)."
    },
    "max_matches": {
      "type": "number",
      "description": "Max passages to return (1–50, default 5)."
    },
    "context_chars": {
      "type": "number",
      "description": "Per-passage character budget (80–4000, default 500)."
    }
  }
}

list_files

Advertised by the server during the last successful anonymous check.

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 packing.

list_files input schema

{
  "type": "object",
  "required": [
    "repo"
  ],
  "properties": {
    "ref": {
      "type": "string",
      "description": "Optional branch, tag or commit SHA (defaults to the default branch)."
    },
    "repo": {
      "type": "string",
      "description": "A GitHub repo as \"owner/repo\" or a github.com URL."
    },
    "exclude": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional glob patterns (support **, *, ?)."
    },
    "include": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional glob patterns (support **, *, ?)."
    }
  }
}

get_file

Advertised by the server during the last successful anonymous check.

Return the full text of a single file in a repository, by path. Use after list_files or search_context to drill in.

get_file input schema

{
  "type": "object",
  "required": [
    "repo",
    "path"
  ],
  "properties": {
    "ref": {
      "type": "string",
      "description": "Optional branch, tag or commit SHA (defaults to the default branch)."
    },
    "path": {
      "type": "string",
      "description": "File path within the repo."
    },
    "repo": {
      "type": "string",
      "description": "A GitHub repo as \"owner/repo\" or a github.com URL."
    }
  }
}

pack_docs

Advertised by the server during the last successful anonymous check.

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 site section; bounded by depth and page count. Use max_tokens to fit a budget.

pack_docs input schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "The absolute http(s) URL to start crawling from (e.g. a docs index)."
    },
    "depth": {
      "type": "number",
      "description": "How many link hops to follow (0–3, default 1)."
    },
    "max_pages": {
      "type": "number",
      "description": "Max pages to fetch (1–30, default 10)."
    },
    "max_tokens": {
      "type": "number",
      "description": "Stop adding pages once the estimate exceeds this many tokens."
    }
  }
}

search_docs

Advertised by the server during the last successful anonymous check.

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 without packing the whole site.

search_docs input schema

{
  "type": "object",
  "required": [
    "url",
    "query"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "The absolute http(s) URL to start crawling from."
    },
    "depth": {
      "type": "number",
      "description": "How many link hops to follow (0–3, default 1)."
    },
    "query": {
      "type": "string",
      "description": "Space-separated search terms; matching is case-insensitive."
    },
    "max_pages": {
      "type": "number",
      "description": "Max pages to fetch (1–30, default 10)."
    },
    "max_matches": {
      "type": "number",
      "description": "Max passages to return (1–50, default 5)."
    },
    "context_chars": {
      "type": "number",
      "description": "Per-passage character budget (80–4000, default 500)."
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 371 ms
95th percentile latency: 371 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 7, 2026, 3:42 AM UTC · probe · passed · 371 ms · metadata changed · 6 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http ctx-mcp https://ctx.vanshul.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add ctx-mcp --url https://ctx.vanshul.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable ctx-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "ctx-mcp": {
      "url": "https://ctx.vanshul.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "ctx-mcp": {
      "type": "streamableHttp",
      "url": "https://ctx.vanshul.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start ctx-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "ctx-mcp": {
      "type": "http",
      "url": "https://ctx.vanshul.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http ctx-mcp https://ctx.vanshul.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://ctx.vanshul.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "ctx-mcp": {
      "serverUrl": "https://ctx.vanshul.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like ctx MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows