CVE-2026-115563modelcontextprotocol python-sdk insufficient verification of data authenticity
CVE-2026-115563 is a insufficient verification of data authenticity in modelcontextprotocol python-sdk, rated high (7.5 on CVSS 3.1).
Why this priority: High severity, with no exploitation signal yet.
Published · Updated · NVD status: Received
What it is
Data is accepted without proof it came from where it claims. Credentials are stored or sent in a way others can recover.
How it is reached
An attacker can exploit it over the network, without an account, and nobody has to click anything.
What an attacker gains
A successful attack can read the data it protects. In practice, this kind of flaw lets an attacker read or tamper with traffic, or pass a forged message as genuine.
Is it being exploited?
There is no public report of exploitation yet. It can be exploited automatically, at scale.
What to do
- Upgrade modelcontextprotocol python-sdk to a fixed version for your release line (1.30.0, 2.2.0).
- Until it is patched, keep it off the internet or behind a VPN, allowlist or authenticating proxy.
Description from NVD
The Model Context Protocol Python SDK is the official Python SDK for Model Context Protocol servers and clients. From 1.9.1 until 1.30.0 and 2.2.0, OAuth client support in mcp.client.auth can send credentials to an authorization server chosen by an untrusted MCP server. ClientCredentialsOAuthProvider and PrivateKeyJWTOAuthProvider cannot identify the authorization server that owns their credentials. Affected HTTP clients using those providers, OAuthClientProvider, or the deprecated 1.x RFC7523OAuthClientProvider can disclose a client_secret, authorization code, PKCE code_verifier, or signed client assertion. MCP servers, stdio clients, and clients that attach their own tokens or headers are not affected. Interactive OAuthClientProvider use requires a person to start sign-in, while the unattended providers do not. For ClientCredentialsOAuthProvider and PrivateKeyJWTOAuthProvider, callers must configure issuer= after upgrading because omission still follows the MCP server's advertised authorization server, and the deprecated RFC7523OAuthClientProvider must be replaced because it has no issuer option. A stored client registration without an issuer remains unbound after upgrading, so stored OAuth client information must be cleared once to register again or a manually pre-registered record must be updated with its issuer. This issue is fixed in versions 1.30.0 and 2.2.0.
What this means for your architecture.
A CVE names a product. Whether it matters depends on where that product sits in your systems: what reaches it, which trust boundary it guards and what it can reach once compromised. Veriom maps your components, their relationships and your trust boundaries from your code, cloud and delivery evidence, so you can see where a component like this sits. The radar itself does not look at your systems.
Components it touches
- TLS termination and service-to-service channels. The flaw sits on the network path between clients and services.
- Signature checks. The flaw sits on the network path between clients and services.
- Credentials kept in code, configuration, images or firmware. The flaw sits between a stored secret and anyone who can read where it is kept.
Trust boundaries in play
- Internet-facing entry points. No account is needed. Any instance reachable from outside your perimeter, through a load balancer, gateway, VPN or exposed admin port, is in scope.
- On the network path between clients and services. An attacker who crosses it can read or tamper with traffic, or pass a forged message as genuine.
- Between a stored secret and anyone who can read where it is kept. An attacker who crosses it can sign in with credentials the vendor shipped or stored unprotected.
Questions to answer about your own systems
- Where does modelcontextprotocol python-sdk run in your systems, and at which version?
- Which of those instances can be reached from the internet or partner networks?
- What can it reach once compromised: which data stores, secrets and services?
Read more
Patches and commits
- github.com/modelcontextprotocol/python-sdk/commit/3eed7ce0a6aba76e8d94c4cfb9b266f41935392c
- github.com/modelcontextprotocol/python-sdk/commit/979208c1157661eac0151f90974a1f96528003fa
- github.com/modelcontextprotocol/python-sdk/commit/d060b36e1d095ef6e93e07ba5d59bb69b2ad449a
- github.com/modelcontextprotocol/python-sdk/pull/3398
- github.com/modelcontextprotocol/python-sdk/pull/3431
- github.com/modelcontextprotocol/python-sdk/pull/3435
Sources
- CVE records and CVSS scores from the NVD CVE API. This product uses the NVD API but is not endorsed or certified by the NVD.
- Exploitation status from CISA’s Known Exploited Vulnerabilities catalog.
- Exploit likelihood from FIRST’s Exploit Prediction Scoring System (EPSS), refreshed daily.
- Explanations are written by Veriom from fixed templates over each record’s data, not by a person reviewing each CVE. Descriptions are quoted from the records as published.