# rmcp OAuth client fetches server-controlled resource_metadata URLs

Advisory record · `GHSA-c9xm-49cp-xcr9`

- **Identifiers:** `GHSA-c9xm-49cp-xcr9`
- **State:** Confirmed
- **Severity:** CVSS 4.0, no score published
- **Critical:** No
- **Weakness (CWE):** [CWE-918](https://cwe.mitre.org/data/definitions/918.html)
- **Tags:** [Server-side request forgery (SSRF)](https://agentprime.io/advisories/tag/ssrf.md)
- **Published:** 2 Oct 2026
- **Updated:** 2 Oct 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 2 Oct 2026, 16:12 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `rmcp` (crates.io): affected `<2.0.0`; fixed in `2.0.0`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> GHSA-c9xm-49cp-xcr9: The rmcp crate (Rust) before 2.0.0 accepts a resource_metadata URL from the WWW-Authenticate header sent by an MCP server and fetches it without same-origin or private-network checks. An attacker who controls or compromises an MCP server that the client connects to can make the client send a GET request to internal addresses such as localhost, private networks, or cloud metadata endpoints, which is a server-side request forgery. Upgrade to rmcp 2.0.0 or later; the source does not describe a workaround.

Written 3 Nov 2026.

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- Score not published, CVSS 4.0: `CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N`, from GitHub Advisory Database

- **CISA KEV:** Not listed.
- **EPSS:** No score.

## Timeline

- 31 Oct 2026, 14:24 UTC: First seen by agentprime
- 31 Oct 2026, 14:24 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-c9xm-49cp-xcr9)

## Sources

- [GitHub Advisory Database: GHSA-c9xm-49cp-xcr9](https://github.com/advisories/GHSA-c9xm-49cp-xcr9)
- [OSV: GHSA-c9xm-49cp-xcr9](https://osv.dev/vulnerability/GHSA-c9xm-49cp-xcr9)
- <https://github.com/modelcontextprotocol/rust-sdk/security/advisories/GHSA-c9xm-49cp-xcr9>
- <https://github.com/modelcontextprotocol/rust-sdk/pull/935>
- <https://github.com/modelcontextprotocol/rust-sdk/commit/eb435c6f51864df74926ef115befce55c16b01ba>
- <https://github.com/modelcontextprotocol/rust-sdk>
- <https://github.com/modelcontextprotocol/rust-sdk/releases/tag/rmcp-v2.0.0>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-c9xm-49cp-xcr9>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-c9xm-49cp-xcr9/>. Everything for agents: <https://agentprime.io/llms.txt>.