GHSA-f897-62hf-6gxq
MCP TypeScript SDK: HTTP server transports and handlers did not limit request body size or JSON-RPC batch length
GHSA-f897-62hf-6gxq is a high vulnerability (CVSS 7.5) in @modelcontextprotocol/sdk, published October 27, 2026. No source lists public exploit code. Fixed in @modelcontextprotocol/sdk 1.30.1.
- Severity
- 7.5 HighCVSS 3.1, GitHub Advisories
- Exploit chance
- UnscoredNo EPSS score yet
- Exploitation
- None knownNot on CISA’s or ENISA’s lists
- Fixed in
1.30.1@modelcontextprotocol/sdk +4 more
Description
Summary
In affected versions, MCP servers reachable over HTTP put no limit on the size of a POST body or on the number of messages in a JSON-RPC batch. Large requests could exhaust the server's memory, and one long batch could block it from serving anyone else. No credentials were needed, unless your application authenticates requests before they reach the SDK.
Am I affected?
Yes, if clients you do not fully trust can reach your server over Streamable HTTP. A body parser such as express.json() does not protect you, because it does not limit batch length. Servers that only use stdio are not affected.
Affected versions:
@modelcontextprotocol/sdk1.10.0 through 1.30.0@modelcontextprotocol/server2.0.0@modelcontextprotocol/node2.0.0@modelcontextprotocol/hono2.0.0
Fix
Upgrade to:
- 1.x:
@modelcontextprotocol/sdk1.30.1 or later - 2.x:
@modelcontextprotocol/server2.1.0,@modelcontextprotocol/node2.1.0 and@modelcontextprotocol/hono2.0.1 or later. Upgrade every one you have installed.
Bodies over 4 MiB now get 413, and batches over 100 messages get 400. If your clients send larger bodies, raise the new maxRequestBodySize option.
If you cannot upgrade yet, cap request body size in a reverse proxy.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- None
- User interaction
- None
What an attacker can affect
- Confidentiality
- None
- Integrity
- None
- Availability
- High
Affected packages
| Package | Affected | Fixed |
|---|---|---|
@modelcontextprotocol/sdknpm | 1.10.0 up to 1.30.1 | 1.30.1 |
@modelcontextprotocol/servernpm | 2.0.0 up to 2.1.0 | 2.1.0 |
@modelcontextprotocol/nodenpm | 2.0.0 up to 2.1.0 | 2.1.0 |
@modelcontextprotocol/hononpm | 2.0.0 up to 2.0.1 | 2.0.1 |
@modelcontextprotocol/sdkTuxCare:npm | 1.29.0-tuxcare.0 up to 1.29.0-tuxcare.6, plus listed versions 1.29.01.29.0-tuxcare.11.29.0-tuxcare.21.29.0-tuxcare.31.29.0-tuxcare.41.29.0-tuxcare.5 | 1.29.0-tuxcare.6 |
What each source reports
GitHub Advisories Score used
MCP TypeScript SDK: HTTP server transports and handlers did not limit request body size or JSON-RPC batch length
Summary
In affected versions, MCP servers reachable over HTTP put no limit on the size of a POST body or on the number of messages in a JSON-RPC batch. Large requests could exhaust the server's memory, and one long batch could block it from serving anyone else. No credentials were needed, unless your application authenticates requests before they reach the SDK.
Am I affected?
Yes, if clients you do not fully trust can reach your server over Streamable HTTP. A body parser such as express.json() does not protect you, because it does not limit batch length. Servers that only use stdio are not affected.
Affected versions:
@modelcontextprotocol/sdk1.10.0 through 1.30.0@modelcontextprotocol/server2.0.0@modelcontextprotocol/node2.0.0@modelcontextprotocol/hono2.0.0
Fix
Upgrade to:
- 1.x:
@modelcontextprotocol/sdk1.30.1 or later - 2.x:
@modelcontextprotocol/server2.1.0,@modelcontextprotocol/node2.1.0 and@modelcontextprotocol/hono2.0.1 or later. Upgrade every one you have installed.
Bodies over 4 MiB now get 413, and batches over 100 messages get 400. If your clients send larger bodies, raise the new maxRequestBodySize option.
If you cannot upgrade yet, cap request body size in a reverse proxy.
- Record
GHSA-f897-62hf-6gxq- CVSS 3.1
- 7.5 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H - Weakness
- CWE-770
- Updated
- 2026-11-02
OSV
MCP TypeScript SDK: HTTP server transports and handlers did not limit request body size or JSON-RPC batch length
Summary
In affected versions, MCP servers reachable over HTTP put no limit on the size of a POST body or on the number of messages in a JSON-RPC batch. Large requests could exhaust the server's memory, and one long batch could block it from serving anyone else. No credentials were needed, unless your application authenticates requests before they reach the SDK.
Am I affected?
Yes, if clients you do not fully trust can reach your server over Streamable HTTP. A body parser such as express.json() does not protect you, because it does not limit batch length. Servers that only use stdio are not affected.
Affected versions:
@modelcontextprotocol/sdk1.10.0 through 1.30.0@modelcontextprotocol/server2.0.0@modelcontextprotocol/node2.0.0@modelcontextprotocol/hono2.0.0
Fix
Upgrade to:
- 1.x:
@modelcontextprotocol/sdk1.30.1 or later - 2.x:
@modelcontextprotocol/server2.1.0,@modelcontextprotocol/node2.1.0 and@modelcontextprotocol/hono2.0.1 or later. Upgrade every one you have installed.
Bodies over 4 MiB now get 413, and batches over 100 messages get 400. If your clients send larger bodies, raise the new maxRequestBodySize option.
If you cannot upgrade yet, cap request body size in a reverse proxy.
- Record
GHSA-f897-62hf-6gxq- CVSS 3.1
- 7.5 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H - Weakness
- CWE-770
- Updated
- 2026-11-02
OSVCLSA-2026-1793630507No score
TuxCare security update for @modelcontextprotocol/sdk (1 CVE)
TuxCare rebuilt @modelcontextprotocol/sdk to address 1 CVE. Fixed in 1.29.0-tuxcare.6.
- Record
CLSA-2026-1793630507- Updated
- 2026-11-02
History
| Recorded | Changed | Sources |
|---|---|---|
| affected, aliases, facts | ||
| first indexed | GitHub Advisories, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
References
github.com/modelcontextprotocol/typescript-sdk/security/advisories/GHSA-f897-62hf-6gxq
Show 5 moreShow less