OAuth2 Authorization Code Collector MCP server
io.github.lonniev/tollbooth-oauth2-collectorlonnievstreamable-httpv0.2.13Scanned
Unauthenticated OAuth2 callback collector for Tollbooth MCP services
4 tools: 1 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 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 OAuth2 Authorization Code Collector MCP server can do
The OAuth2 Authorization Code Collector MCP server is published by the GitHub account lonniev. It has 4 tools. It can create or change data (1 tool: store_code), but cannot delete data. 3 tools only read.
None of its tools reads private data, brings in text other people write, or sends data 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, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 20, 2026, version 0.2.13.
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.
4 tools
Changes things 1Claude Code: ask
store_codeStore a sealed OAuth2 authorization code.No findings
Why it is in this group
- The name "store_code" says "store": a word for a change.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
Description, as the server wrote it Store a sealed OAuth2 authorization code. Called by the serverless callback function after the browser redirect. The ``state`` carries the patron npub, the operator npub (the PUBLIC key the code is sealed to) and the flow's one-time secret — see the SDK's ``pack_oauth_state``. The code is sealed with NIP-44 to the operator so only that operator's nsec can open it. The Neon row is keyed by ``oauth_code_key(state)`` (patron npub + secret), so only the flow that holds the secret finds it: a link someone else built with a patron's npub files its code where that patron's flow never looks.
Only reads 3Show 3 read-only tools
collector_statusHealth check — shows the number of pending authorization codes and TTL.No findings
Why it is in this group
- The name "collector_status" says "status": a word for reading.
Description, as the server wrote it Health check — shows the number of pending authorization codes and TTL.
retrieve_codeRetrieve a stored authorization code (one-time read, auto-deleted).No findings
Why it is in this group
- The name "retrieve_code" says "retrieve": a word for reading.
Description, as the server wrote it Retrieve a stored authorization code (one-time read, auto-deleted). Called by the originating MCP server to pick up the code after the user has authorized in the browser. Returns the encrypted code which the caller decrypts using the same state token.
service_statusReport the running build so a redeploy can be verified.No findings
Why it is in this group
- The name "service_status" says "status": a word for reading.
Description, as the server wrote it Report the running build so a redeploy can be verified. Free. Delegates to the SDK's canonical ``build_service_status`` — the single source of the service_status payload shape — so this collector reports the same envelope as every other DPYC service. The load-bearing field is ``build_info.fastmcp_cloud_git_commit_sha``: the commit Horizon actually deployed. The post-merge deploy-verify probe reads it to confirm the live service redeployed the merged sha; with no ``service_status`` tool to probe, that sha reads as ``<none>`` and an otherwise-healthy deploy is flagged as "did not land". The vault/courier/operator fields are ``False``/empty by construction — this is an unauthenticated community utility with no operator runtime.
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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
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, 19:28 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://tollbooth-oauth2-collector.fastmcp.app/mcp: tools/list returned 4 tools to an anonymous client, including store_code (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.
Tools2 changed.~2 changedView diff
- Changed:retrieve_codeOnly readsinputSchema
- Changed:store_codeChanges thingsdescriptioninputSchema
Install
Pinned to version 0.2.13. Values in angle brackets are yours to fill in.
claude mcp add --transport http tollbooth-oauth2-collector https://tollbooth-oauth2-collector.fastmcp.app/mcpclaude mcp add --transport http tollbooth-oauth2-collector https://tollbooth-oauth2-collector.fastmcp.app/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__tollbooth-oauth2-collector__retrieve_code",
"mcp__tollbooth-oauth2-collector__collector_status",
"mcp__tollbooth-oauth2-collector__service_status"
],
"ask": [
"mcp__tollbooth-oauth2-collector__store_code"
],
"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 tollbooth-oauth2-collector. Review it before you use it.
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.lonniev/tollbooth-oauth2-collector/verify?hash=6a858d8002966751e64181b2eabbac3a055b109b50564f358e2a7dca629a9687" | jq -e '.changed == false'Pinned hash 6a858d800296, from Nov 20, 2026, 04:19 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.lonniev/tollbooth-oauth2-collector/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.lonniev/tollbooth-oauth2-collector)Source: MCP Registry · repository. Synced Nov 20, 2026, 04:17 UTC.
OAuth2 Authorization Code Collector MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the OAuth2 Authorization Code Collector MCP server safe?
- No scan can promise that. What its definitions show: 4 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 OAuth2 Authorization Code Collector MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the OAuth2 Authorization Code Collector 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 OAuth2 Authorization Code Collector MCP server have?
- 4 tools: 1 write, 3 read. store_code, retrieve_code, collector_status and service_status.
Does the OAuth2 Authorization Code Collector MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the OAuth2 Authorization Code Collector MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the OAuth2 Authorization Code Collector MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 7, 2026. Every change is on this page and in its Atom feed.