ctx MCP server
io.github.vanshulgoyal101/ctxvanshulgoyal101streamable-httpv1.0.0Scanned
Turn a GitHub repo or docs site into agent-ready context: pack it or search it, over MCP.
6 tools: 1 change things and 5 only read.
- Reads private data · 5
- Reads text others write · 2
- Can send data out · 2
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the ctx MCP server can do
The ctx MCP server is published by the GitHub account vanshulgoyal101. It has 6 tools. It can create or change data (1 tool: pack_docs), but cannot delete data. 5 tools only read.
5 tools read private data (pack_repo, search_context, list_files and 2 more); 2 tools bring in text other people can write (pack_docs and search_docs); 2 tools can send data out of your system (pack_docs and search_docs). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
6 tools
Changes things 1Claude Code: ask
pack_docsCrawl 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.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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.
Only reads 5Show 5 read-only tools
get_fileReturn the full text of a single file in a repository, by path.Reads private dataNo findings
Why it is in this group
- The name "get_file" says "get": a word for reading.
What it can reach
- private-dataThe name "get_file" says "get" and "file": it reads files.
- private-dataThe description's first sentence says "return" and "file": it reads files.
- private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
Description, as the server wrote it Return the full text of a single file in a repository, by path. Use after list_files or search_context to drill in.
list_filesList the text files ctx would include for a repository (after stripping binaries, lockfiles and build dirs), with their byte sizes.Reads private dataNo findings
Why it is in this group
- The name "list_files" says "list": a word for reading.
What it can reach
- private-dataThe name "list_files" says "list" and "file": it reads files.
- private-dataThe description's first sentence says "list" and "file": it reads files.
- private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
Description, as the server wrote it 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.
pack_repoFetch 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…Reads private dataNo findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
What it can reach
- private-dataThe name "pack_repo" says "repo": it reads repositories.
- private-dataThe description's first sentence says "fetch" and "repository": it reads repositories.
- private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
Description, as the server wrote it 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.
search_contextSearch a GitHub repository and return only the passages that match a query — each with its file path, line number and a relevance score.Reads private dataNo findings
Why it is in this group
- The name "search_context" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "repository": it reads repositories.
- private-dataThe input names a repo (input.repo), and the tool reads: it reads repositories.
Description, as the server wrote it 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_docsCrawl a documentation site and return only the passages that match a query — each with its page URL, line and a relevance score.Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "search_docs" says "search": a word for reading.
What it can reach
- private-dataThe name "search_docs" says "search" and "doc": it reads documents.
- untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it 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.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
20 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.
- Reads private data5
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__ctx__pack_docs",
"mcp__ctx__search_docs"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:12 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://ctx.vanshul.com/mcp: tools/list returned 6 tools to an anonymous client, including pack_docs (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http ctx https://ctx.vanshul.com/mcpclaude mcp add --transport http ctx https://ctx.vanshul.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__ctx__pack_repo",
"mcp__ctx__search_context",
"mcp__ctx__list_files",
"mcp__ctx__get_file"
],
"ask": [
"mcp__ctx__pack_docs",
"mcp__ctx__search_docs"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as ctx. Review it before you use it.
Capability tags behind 6 rules
- mcp__ctx__pack_repo private-data
- mcp__ctx__search_context private-data
- mcp__ctx__list_files private-data
- mcp__ctx__get_file private-data
- mcp__ctx__pack_docs untrusted-input, outbound
- mcp__ctx__search_docs private-data, untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.vanshulgoyal101/ctx/verify?hash=32920d65185b1f43939c109758f24b7e0329699fd9e09e1950c919e980ff2ccf" | jq -e '.changed == false'Pinned hash 32920d65185b, from Nov 20, 2026, 17:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.vanshulgoyal101/ctx/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.vanshulgoyal101/ctx)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:51 UTC.
ctx MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ctx MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the ctx MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the ctx MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the ctx MCP server have?
- 6 tools: 1 write, 5 read. pack_docs, pack_repo, search_context, list_files, get_file and search_docs.
Does the ctx MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ctx MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): pack_docs and search_docs.
Has the ctx MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.