CVE-2026-101057 Vulnerability Analysis & Exploit Details

CVE-2026-101057 Vulnerability Summary

CVE-2026-101057: utcp-mcp (the MCP plugin of python-utcp) through 1.1.2 connects to the HTTP and WebSocket MCP server URLs given in a call template's mcpServers configuration without the ensure_secure_url validation that the HTTP-family plugins apply, so the HTTPS/WSS-or-loopback rule is not enforced. A call template naming a plain-HTTP, non-loopback MCP server URL is dialed as configured, exposing the MCP handshake to network interception and permitting cleartext connections to internal hosts. The mcpServers configuration is operator-authored rather than remote data, and the connection is an MCP handshake rather than an arbitrary request returning a body, which limits practical exploitation; the OAuth2 token_url credential path described in the original report was not reachable in the affected versions, because the OAuth2 handler was never invoked and the call template's auth field was not read. Fixed in utcp-mcp 1.1.3, which validates server URLs before any connection is made.

CVE-2026-101057 References

External References

• https://github.com/universal-tool-calling-protocol/python-utcp/security/advisories/GHSA-qwr9-cj2c-v3fv
• https://www.vulncheck.com/advisories/utcp-mcp-before-1.1.3-ssrf-via-unvalidated-mcp-server-url

CWE Common Weakness Enumeration

CAPEC Common Attack Pattern Enumeration and Classification

• Session Sidejacking CAPEC-102 Session sidejacking takes advantage of an unencrypted communication channel between a victim and target system. The attacker sniffs traffic on a network looking for session tokens in unencrypted traffic. Once a session token is captured, the attacker performs malicious actions by using the stolen token with the targeted application to impersonate the victim. This attack is a specific method of session hijacking, which is exploiting a valid session token to gain unauthorized access to a target system or information. Other methods to perform a session hijacking are session fixation, cross-site scripting, or compromising a user or server machine and stealing the session token.
• Interception CAPEC-117 An adversary monitors data streams to or from the target for information gathering purposes. This attack may be undertaken to solely gather sensitive information or to support a further attack against the target. This attack pattern can involve sniffing network traffic as well as other types of data streams (e.g. radio). The adversary can attempt to initiate the establishment of a data stream or passively observe the communications as they unfold. In all variants of this attack, the adversary is not the intended recipient of the data stream. In contrast to other means of gathering information (e.g., targeting data leaks), the adversary must actively position themself so as to observe explicit data channels (e.g. network traffic) and read the content. However, this attack differs from a Adversary-In-the-Middle (CAPEC-94) attack, as the adversary does not alter the content of the communications nor forward data to the intended recipient.
• Harvesting Information via API Event Monitoring CAPEC-383 An adversary hosts an event within an application framework and then monitors the data exchanged during the course of the event for the purpose of harvesting any important data leaked during the transactions. One example could be harvesting lists of usernames or userIDs for the purpose of sending spam messages to those users. One example of this type of attack involves the adversary creating an event within the sub-application. Assume the adversary hosts a "virtual sale" of rare items. As other users enter the event, the attacker records via AiTM (CAPEC-94) proxy the user_ids and usernames of everyone who attends. The adversary would then be able to spam those users within the application using an automated script.
• Signature Spoofing by Mixing Signed and Unsigned Content CAPEC-477 An attacker exploits the underlying complexity of a data structure that allows for both signed and unsigned content, to cause unsigned data to be processed as though it were signed data.
• Sniff Application Code CAPEC-65 An adversary passively sniffs network communications and captures application code bound for an authorized client. Once obtained, they can use it as-is, or through reverse-engineering glean sensitive information or exploit the trust relationship between the client and server. Such code may belong to a dynamic update to the client, a patch being applied to a client component or any such interaction where the client is authorized to communicate with the server.

Other 5 Recently Published CVEs Vulnerabilities

• CVE-2026-101061 – utcp-gql before 1.1.1 and utcp-websocket before 1.1.1 contain server-side request forgery vulnerabilities due to incomplete application of CVE-2026...
• CVE-2026-101060 – python-utcp versions before 1.1.4 contain a server-side request forgery vulnerability in HttpCommunicationProtocol.call_tool that validates the ini...
• CVE-2026-101059 – utcp-http before 1.1.4 fails to validate the OAuth2 tokenUrl field from remote OpenAPI specifications, allowing attackers to redirect credential su...
• CVE-2026-101058 – python-utcp (pip package utcp-http) before 1.1.12 does not verify whether tool URLs declared in a hand-written UTCP manual point at the agent's own...
• CVE-2026-101057 – utcp-mcp (the MCP plugin of python-utcp) through 1.1.2 connects to the HTTP and WebSocket MCP server URLs given in a call template's mcpServers con...