coderegistry MCP server
io.github.hellosg/coderegistryhellosgstreamable-httpv1.0.0Scanned
Enterprise code intelligence for M&A, security audits, and tech debt. Hosted server with 200k free.
23 tools: 3 can delete or cancel things, 5 change things and 15 only read.
- Reads private data · 12
- Reads text others write · 2
- Can send data out · 1
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here can delete or cancel things. Govern them.
- 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 coderegistry MCP server can do
The coderegistry MCP server is published by the GitHub account hellosg. It has 23 tools. It can delete or cancel things (3 tools: delete_project, delete-code-vault and delete_account) and create or change data (5 tools: create_account, create_project, create-code-vault, reanalyze-code-vault and 1 more). 15 tools only read.
12 tools read private data (list_vaults, get_vault, get-code-vault-summary and 9 more); 2 tools bring in text other people can write (get-security-issues and get-components); 1 tool can send data out of your system (get-components). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 2 findings (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 19, 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.
23 tools
Deletes or cancels 3Claude Code: deny
delete_accountDeletes the team account plus all projects and vaults.No findings
Why it is in this group
- The name "delete_account" says "delete": a word for removing or ending something.
Description, as the server wrote it Deletes the team account plus all projects and vaults. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
delete_projectDeletes a project and its vaults.No findings
Why it is in this group
- The name "delete_project" says "delete": a word for removing or ending something.
Description, as the server wrote it Deletes a project and its vaults. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
delete-code-vaultDeletes a code vault and related analysis data.No findings
Why it is in this group
- The name "delete-code-vault" says "delete": a word for removing or ending something.
Description, as the server wrote it Deletes a code vault and related analysis data. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
Changes things 5Claude Code: ask
create_accountCreates a new Code Registry account and returns API credentials.1 finding
Why it is in this group
- The name "create_account" says "create": a word for a change.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...w Code Registry account and returns API credentials. Required fields: email (account owner'..."
Description, as the server wrote it Creates a new Code Registry account and returns API credentials. Required fields: email (account owner's email), name (account owner's full name), team_name (team or company name). All three must be provided or the call will fail. Cold starts can cause the first request to time out; retry with backoff. No API key required.
create_projectCreates a project for a team user.No findings
Why it is in this group
- The name "create_project" says "create": a word for a change.
Description, as the server wrote it Creates a project for a team user. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
create-code-vaultCreates a code vault and queues the initial analysis.1 finding
Why it is in this group
- The name "create-code-vault" says "create": a word for a change.
Findings
- Info
The input schema at properties.source_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.source_type.description: "...reachable repo URL; private repos need credentials."
Description, as the server wrote it Creates a code vault and queues the initial analysis. Choose source_type based on what is available in your environment: (1) LOCAL_AGENT — preferred when Docker is available; runs a local container, source code never leaves the machine. The response includes next_steps.commands that MUST be executed to start the agent. (2) FILE_ARCHIVE — use this when Docker is NOT available (e.g. sandboxed/browser environments). This requires uploading the project's source code to a third-party file host, so you MUST first explain this to the user and get their explicit confirmation before zipping or uploading anything. If the user does not confirm, do not proceed with FILE_ARCHIVE. Once confirmed, zip the project files, upload the zip to a temporary direct-download URL (e.g. file.io, gofile.io, tmpfiles.org), then pass that URL as source_url. After the analysis is complete, recommend that the user deletes the uploaded file from the file host (or delete it yourself if the user agrees and the host supports it). (3) GIT — only when the user provides a reachable repo URL. Private repos require username and password/token. Cold starts can cause the first request to time out; retry with backoff. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
reanalyze-code-vaultCreates a new analysis version for an existing code vault using its existing source settings.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Creates a new analysis version for an existing code vault using its existing source settings. For LOCAL_AGENT, the response includes next_steps.commands and the local agent must be run again. For GIT/FILE_ARCHIVE, the re-analysis of the original code source is queued automatically. Note: summary/results/report tools always return the latest version only, so reanalysis replaces access to prior version data. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
rotate_api_keyIssues a fresh integrator API key.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Issues a fresh integrator API key. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
Only reads 15Show 15 read-only tools
get_accountReturns the team owner account information.No findings
Why it is in this group
- The name "get_account" says "get": a word for reading.
Description, as the server wrote it Returns the team owner account information. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
get_projectReturns a specific project by id.No findings
Why it is in this group
- The name "get_project" says "get": a word for reading.
Description, as the server wrote it Returns a specific project by id. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
get_vaultReturns a specific vault by id.Reads private dataNo findings
Why it is in this group
- The name "get_vault" says "get": a word for reading.
What it can reach
- private-dataThe name "get_vault" says "get" and "vault": it reads secrets.
- private-dataThe description's first sentence says "return" and "vault": it reads secrets.
Description, as the server wrote it Returns a specific vault by id. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
get-code-iq-automated-queriesReturns trimmed Code IQ automated analyses (architecture, scalability, EOL, AI functionality, etc.) for a project (aggregated) or a single vault.Reads private dataNo findings
Why it is in this group
- The name "get-code-iq-automated-queries" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "vault": it reads secrets.
Description, as the server wrote it Returns trimmed Code IQ automated analyses (architecture, scalability, EOL, AI functionality, etc.) for a project (aggregated) or a single vault. Excludes The Code Score — use get-the-code-score for that, and do not pass analysis_key=code_score here (404). Only cached results are returned; this never triggers a fresh analysis. Provide exactly one of project_id or vault_id. Requires full data access (a paid plan; verification-only plans are not included). Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
get-code-smellsReturns code smell findings for a project (all vaults) or a single vault.Reads private dataNo findings
Why it is in this group
- The name "get-code-smells" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "vault": it reads secrets.
- private-dataThe input names a file (input.file), and the tool reads: it reads files.
Description, as the server wrote it Returns code smell findings for a project (all vaults) or a single vault. Provide exactly one of project_id or vault_id. Requires full data access (a paid plan; verification-only plans are not included). Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
get-code-vault-reportsReturns report URLs (snapshot/comparison) for a vault.Reads private dataNo findings
Why it is in this group
- The name "get-code-vault-reports" says "get": a word for reading.
What it can reach
- private-dataThe name "get-code-vault-reports" says "get" and "vault": it reads secrets.
- private-dataThe description's first sentence says "return" and "vault": it reads secrets.
Description, as the server wrote it Returns report URLs (snapshot/comparison) for a vault. Completion rules: if version is 1.0.0, snapshot indicates completion and comparison is null; for versions above 1.0.0, comparison indicates completion. If not ready, retry with exponential backoff (5s, 10s, 20s, 40s, max 60s). This endpoint always returns the latest version only; once reanalysis starts, prior versions are no longer accessible here. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
get-code-vault-resultsReturns analysis results for a vault.Reads private dataNo findings
Why it is in this group
- The name "get-code-vault-results" says "get": a word for reading.
What it can reach
- private-dataThe name "get-code-vault-results" says "get" and "vault": it reads secrets.
- private-dataThe description's first sentence says "return" and "vault": it reads secrets.
Description, as the server wrote it Returns analysis results for a vault. Free-tier teams receive summary-only results; paid teams receive full facet data and AI insights. Analysis is async; if status is 'processing', poll with exponential backoff (5s, 10s, 20s, 40s, max 60s). Analysis can be as quick as 20-30 minutes for under 500,000 lines of code. Larger codebases can take much longer, especially with the security scan. Facet meanings are documented in resources://docs/facets; AI Quotient is a code-quality metric (not AI-generated code). AI insights can take a few minutes after analysis completes; if ai_insights is empty, poll again and check ai_insights_status per facet (ready/processing/not_available). This endpoint always returns the latest version only; once reanalysis starts, prior versions are no longer accessible here. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
get-code-vault-summaryReturns the latest version/status info for a vault.Reads private dataNo findings
Why it is in this group
- The name "get-code-vault-summary" says "get": a word for reading.
What it can reach
- private-dataThe name "get-code-vault-summary" says "get" and "vault": it reads secrets.
- private-dataThe description's first sentence says "return" and "vault": it reads secrets.
Description, as the server wrote it Returns the latest version/status info for a vault. Analysis is async; if status is 'processing', poll with exponential backoff (5s, 10s, 20s, 40s, max 60s). Analysis can be as quick as 20-30 minutes for under 500,000 lines of code. Larger codebases can take much longer, especially with the security scan. This endpoint always returns the latest version only; once reanalysis starts, prior versions are no longer accessible here. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
get-componentsReturns detected open-source/CMS components for a project (all vaults) or a single vault.Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "get-components" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "vault": it reads secrets.
- 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 Returns detected open-source/CMS components for a project (all vaults) or a single vault. Provide exactly one of project_id or vault_id. Requires full data access (a paid plan; verification-only plans are not included). Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
get-contributorsReturns aggregated contributor stats (commit count, lines added/deleted, first/last commit) for a project (all vaults) or a single vault.Reads private dataNo findings
Why it is in this group
- The name "get-contributors" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "commit": it reads repositories.
Description, as the server wrote it Returns aggregated contributor stats (commit count, lines added/deleted, first/last commit) for a project (all vaults) or a single vault. Provide exactly one of project_id or vault_id. Requires full data access (a paid plan; verification-only plans are not included). Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
get-git-historyReturns git commit history for a project (all vaults) or a single vault.Reads private dataNo findings
Why it is in this group
- The name "get-git-history" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "commit": it reads repositories.
Description, as the server wrote it Returns git commit history for a project (all vaults) or a single vault. Provide exactly one of project_id or vault_id. Requires full data access (a paid plan; verification-only plans are not included). Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
get-security-issuesReturns deduplicated security findings for a project (all vaults) or a single vault.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get-security-issues" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "vault": it reads secrets.
- private-dataThe input names a file (input.file), and the tool reads: it reads files.
- untrusted-inputThe name "get-security-issues" says "get" and "issue": it reads issues, which other people can write.
Description, as the server wrote it Returns deduplicated security findings for a project (all vaults) or a single vault. Provide exactly one of project_id or vault_id. Requires full data access (a paid plan; verification-only plans are not included). Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
get-the-code-scoreReturns The Code Score (security/code-quality/dependencies, 1000 points) for a project (aggregated) or a single vault.Reads private dataNo findings
Why it is in this group
- The name "get-the-code-score" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "vault": it reads secrets.
Description, as the server wrote it Returns The Code Score (security/code-quality/dependencies, 1000 points) for a project (aggregated) or a single vault. Provide exactly one of project_id or vault_id. Requires full data access (a paid plan; verification-only plans are not included). If the plan doesn't include Code Score access, or it hasn't been generated yet, returns the same response shape with empty sections/priorities rather than an error. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
list_projectsLists all projects for the authenticated team.No findings
Why it is in this group
- The name "list_projects" says "list": a word for reading.
Description, as the server wrote it Lists all projects for the authenticated team. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
list_vaultsLists vaults within a project.Reads private dataNo findings
Why it is in this group
- The name "list_vaults" says "list": a word for reading.
What it can reach
- private-dataThe name "list_vaults" says "list" and "vault": it reads secrets.
- private-dataThe description's first sentence says "list" and "vault": it reads secrets.
Description, as the server wrote it Lists vaults within a project. Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.
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.
24 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data12
- 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 out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__coderegistry__get-components"
]
}
}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, 19:05 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
- 8
- Protocol version
- 2025-11-25
- 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 8 tools that change things (3 destructive, 5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://integrator.app.thecoderegistry.com/api/ai/router: tools/list returned 23 tools to an anonymous client, including delete_project (destructive), delete-code-vault (destructive), delete_account (destructive), create_account (write), create_project (write) and 3 more
Findings
Matches of fixed checks, with the text they matched.
- Infocreate_account
The description mentions "credentials".
What this check looks forMatched text
description: "...w Code Registry account and returns API credentials. Required fields: email (account owner'..."
The input schema at properties.source_type.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.source_type.description: "...reachable repo URL; private repos need credentials."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 changed.~1 changedView diff
- Changed:create-code-vaultChanges thingsdescriptioninputSchema
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http coderegistry https://integrator.app.thecoderegistry.com/api/ai/routerclaude mcp add --transport http coderegistry https://integrator.app.thecoderegistry.com/api/ai/routerRun 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__coderegistry__list_projects",
"mcp__coderegistry__get_project",
"mcp__coderegistry__list_vaults",
"mcp__coderegistry__get_vault",
"mcp__coderegistry__get-code-vault-summary",
"mcp__coderegistry__get-code-vault-results",
"mcp__coderegistry__get-code-vault-reports",
"mcp__coderegistry__get_account",
"mcp__coderegistry__get-security-issues",
"mcp__coderegistry__get-code-smells",
"mcp__coderegistry__get-git-history",
"mcp__coderegistry__get-contributors",
"mcp__coderegistry__get-code-iq-automated-queries",
"mcp__coderegistry__get-the-code-score"
],
"ask": [
"mcp__coderegistry__create_account",
"mcp__coderegistry__create_project",
"mcp__coderegistry__create-code-vault",
"mcp__coderegistry__reanalyze-code-vault",
"mcp__coderegistry__rotate_api_key",
"mcp__coderegistry__get-components"
],
"deny": [
"mcp__coderegistry__delete_project",
"mcp__coderegistry__delete-code-vault",
"mcp__coderegistry__delete_account"
]
}
}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 coderegistry. Review it before you use it.
Capability tags behind 12 rules
- mcp__coderegistry__list_vaults private-data
- mcp__coderegistry__get_vault private-data
- mcp__coderegistry__get-code-vault-summary private-data
- mcp__coderegistry__get-code-vault-results private-data
- mcp__coderegistry__get-code-vault-reports private-data
- mcp__coderegistry__get-security-issues private-data, untrusted-input
- mcp__coderegistry__get-code-smells private-data
- mcp__coderegistry__get-git-history private-data
- mcp__coderegistry__get-contributors private-data
- mcp__coderegistry__get-components private-data, untrusted-input, outbound
- mcp__coderegistry__get-code-iq-automated-queries private-data
- mcp__coderegistry__get-the-code-score private-data
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.hellosg/coderegistry/verify?hash=c53706914e6d100a9009a675377dc479690592c3b2ca8e860899f4a663ffd936" | jq -e '.changed == false'Pinned hash c53706914e6d, from Nov 19, 2026, 20:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.hellosg/coderegistry/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.hellosg/coderegistry)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:35 UTC.
coderegistry MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the coderegistry MCP server safe?
- No scan can promise that. What its definitions show: 23 tools, 8 of which can change, send or delete something, and 2 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 coderegistry MCP server delete data?
- Yes. 3 tools can delete, cancel or revoke something: delete_project, delete-code-vault and delete_account.
Can the coderegistry 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 coderegistry MCP server have?
- 23 tools: 3 destructive, 5 write, 15 read. delete_project, delete-code-vault, delete_account, create_account, create_project, create-code-vault, reanalyze-code-vault, rotate_api_key and 15 more.
Does the coderegistry MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the coderegistry MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): get-components.
Has the coderegistry MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.