BREW-MCP-PROXY-CVE-2026-59951 (GHSA-84M7-P3X7-PCFV)
Vulnerability from osv_homebrew – Published: 2026-10-16 09:39 – Updated: 2026-10-16 09:39 – Source websiteSummary
In affected versions, a Streamable HTTP server in stateful mode (the default) never reclaimed session state:
- sessions did not expire;
- a client
DELETEended the session but left its entry registered; - a session whose first request was refused stayed registered with a running task.
Each session also kept its parsed initialize parameters, and the number of sessions was unlimited. A client that could reach the endpoint could grow server memory without bound using ordinary short requests; only a restart reclaimed it.
Am I affected?
Yes, if you serve MCP over Streamable HTTP in stateful mode and clients you do not fully trust can reach the endpoint. Stateful mode is the default for:
FastMCP(1.x)MCPServerandServer.streamable_http_app()(2.x)StreamableHTTPSessionManager
Affected versions: 1.8.0 through 1.29.1, and 2.0.0 through 2.1.1.
Not affected:
- servers on 1.12.0 or later passing
stateless_http=True(no sessions are kept) - servers using only the stdio or SSE transports
Authentication limits who can open sessions, not how many a token holder can open.
Fix
Upgrade to mcp 1.30.0 (1.x) or 2.2.0 (2.x) or later. In those versions:
- a session with no request in flight for
session_idle_timeoutseconds (default 1800) is closed and its ID then answers404; open streams and in-progress requests keep it alive; - at most
max_sessionssessions exist at once (default 10000); a request that would open another is answered503; - a session is discarded as soon as it ends, whether by
DELETE, expiry, or a refused opening request.
Both settings are keyword arguments on FastMCP(...) (1.x), MCPServer.run() / streamable_http_app() (2.x) and StreamableHTTPSessionManager; None disables them.
This bounds retention rather than eliminating it: a live session still holds its initialize parameters (up to roughly twice the 4 MiB body limit), and an initialize with invalid parameters still opens a session that expires like any other. On a small host, lower session_idle_timeout, max_sessions and max_request_body_size to fit.
If you cannot upgrade yet, pass stateless_http=True (1.12.0 or later) where you need no per-session state, or restrict who can reach the endpoint.
{
"affected": [
{
"ecosystem_specific": {
"fix": "bump",
"range_state": "fixed",
"resource": "mcp",
"resource_purl": "pkg:pypi/mcp@1.30.0",
"upstream_fixed_in": "1.30.0"
},
"package": {
"ecosystem": "Homebrew",
"name": "mcp-proxy",
"purl": "pkg:brew/mcp-proxy"
},
"ranges": [
{
"events": [
{
"introduced": "0.8.2"
},
{
"fixed": "0.12.0_5"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"database_specific": {
"confidence": "high",
"source": "matched",
"strategy": "registry",
"upstream_evidence": [
{
"ecosystem": "PyPI",
"key": "pkg:pypi/mcp@1.30.0",
"name": "mcp",
"resource": "mcp",
"strategy": "registry",
"subject_version": "1.30.0"
}
]
},
"details": "### Summary\nIn affected versions, a Streamable HTTP server in stateful mode (the default) never reclaimed session state:\n\n- sessions did not expire;\n- a client `DELETE` ended the session but left its entry registered;\n- a session whose first request was refused stayed registered with a running task.\n\nEach session also kept its parsed `initialize` parameters, and the number of sessions was unlimited. A client that could reach the endpoint could grow server memory without bound using ordinary short requests; only a restart reclaimed it.\n\n### Am I affected?\nYes, if you serve MCP over Streamable HTTP in stateful mode and clients you do not fully trust can reach the endpoint. Stateful mode is the default for:\n\n- `FastMCP` (1.x)\n- `MCPServer` and `Server.streamable_http_app()` (2.x)\n- `StreamableHTTPSessionManager`\n\nAffected versions: 1.8.0 through 1.29.1, and 2.0.0 through 2.1.1.\n\nNot affected:\n\n- servers on 1.12.0 or later passing `stateless_http=True` (no sessions are kept)\n- servers using only the stdio or SSE transports\n\nAuthentication limits who can open sessions, not how many a token holder can open.\n\n### Fix\nUpgrade to `mcp` 1.30.0 (1.x) or 2.2.0 (2.x) or later. In those versions:\n\n- a session with no request in flight for `session_idle_timeout` seconds (default 1800) is closed and its ID then answers `404`; open streams and in-progress requests keep it alive;\n- at most `max_sessions` sessions exist at once (default 10000); a request that would open another is answered `503`;\n- a session is discarded as soon as it ends, whether by `DELETE`, expiry, or a refused opening request.\n\nBoth settings are keyword arguments on `FastMCP(...)` (1.x), `MCPServer.run()` / `streamable_http_app()` (2.x) and `StreamableHTTPSessionManager`; `None` disables them.\n\nThis bounds retention rather than eliminating it: a live session still holds its `initialize` parameters (up to roughly twice the 4 MiB body limit), and an `initialize` with invalid parameters still opens a session that expires like any other. On a small host, lower `session_idle_timeout`, `max_sessions` and `max_request_body_size` to fit.\n\nIf you cannot upgrade yet, pass `stateless_http=True` (1.12.0 or later) where you need no per-session state, or restrict who can reach the endpoint.",
"id": "BREW-mcp-proxy-CVE-2026-59951",
"modified": "2026-10-16T09:39:29Z",
"published": "2026-10-16T09:39:29Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/modelcontextprotocol/python-sdk/security/advisories/GHSA-84m7-p3x7-pcfv"
},
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-59951"
},
{
"type": "WEB",
"url": "https://github.com/modelcontextprotocol/python-sdk/pull/3395"
},
{
"type": "WEB",
"url": "https://github.com/modelcontextprotocol/python-sdk/pull/3426"
},
{
"type": "WEB",
"url": "https://github.com/modelcontextprotocol/python-sdk/commit/92120b4b0f50385af096592d7cee932fc1d994e7"
},
{
"type": "WEB",
"url": "https://github.com/modelcontextprotocol/python-sdk/commit/d2290ca3434731b68ea3e2270bc06a6e6575931b"
},
{
"type": "PACKAGE",
"url": "https://github.com/modelcontextprotocol/python-sdk"
},
{
"type": "WEB",
"url": "https://github.com/modelcontextprotocol/python-sdk/releases/tag/v1.30.0"
},
{
"type": "WEB",
"url": "https://github.com/modelcontextprotocol/python-sdk/releases/tag/v2.2.0"
}
],
"schema_version": "1.7.3",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
"type": "CVSS_V3"
},
{
"score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N",
"type": "CVSS_V4"
}
],
"summary": "MCP Python SDK: Unbounded Session Accumulation in StreamableHTTP Transport Enables Resource Exhaustion",
"upstream": [
"GHSA-84m7-p3x7-pcfv",
"CVE-2026-59951"
]
}
Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline
Sightings and recorded dates, grouped by day · UTC
Loading timeline…
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.