high CVSS 7.6 EPSS 0.24%

CVE-2026-52870·Python vulnerability

The MCP Python SDK, called mcp on PyPI, is a Python implementation of the Model Context Protocol (MCP). From 1.23.0 until 1.27.2, default handlers installed by server.experimental.enable_tasks() for tasks/list, tasks/get, tasks/result, and tasks/cancel operate only on task identifiers without recording the session that created each task, allowing any connected client to enumerate, read results from, consume messages for, or cancel other clients' tasks. This issue is fixed in version 1.27.2.

Severity
high
Software
Python
Fixed in
1.27.2
Published

How likely is exploitation

FIRST's Exploit Prediction Scoring System puts the probability of this CVE being exploited in the next 30 days at 0.24% — higher than 15% of all published CVEs. EPSS is an independent forecast of exploitation, not a severity rating: it says nothing about how much damage a successful attack does, which is what a CVSS score measures.

Read the two together. CVE-2026-52870 scores 7.6 on CVSS, so a successful attack would be serious — but at 0.24%, almost nobody is currently attempting it. That is a different situation from a flaw under mass exploitation, and it is usually the difference between patching on your next maintenance window and patching tonight.

Affected versions

From: 1.23.0

Until: 1.27.2

Fixed in: 1.27.2

How to fix this CVE

Upgrade the MCP Python SDK to version 1.27.2 or later to remediate a critical cross-client task isolation vulnerability. Organizations using server.experimental.enable_tasks() must apply this update immediately, as it prevents unauthorized clients from accessing, modifying, or canceling other clients' task data. Verify the upgrade by checking the installed mcp package version after deployment.

sudo dnf update python3-mcp

Defensia detects this vulnerability

How to check if you are affected

  1. Step 1: Check the installed MCP SDK version by running: python3 -c "import mcp; print(mcp.__version__)" or pip3 show mcp | grep Version
  2. Step 2: Verify if server.experimental.enable_tasks() is active in your MCP server configuration by grepping your codebase: grep -r "enable_tasks" /path/to/mcp/config/
  3. Step 3: Review MCP server logs for task operation requests (tasks/list, tasks/get, tasks/result, tasks/cancel) from multiple distinct clients to identify cross-client access patterns: grep -E "tasks/(list|get|result|cancel)" /var/log/mcp-server.log
  4. Step 4: After upgrading to 1.27.2+, confirm the fix by re-running python3 -c "import mcp; print(mcp.__version__)" and verifying session isolation is enforced in new task operations

FAQ

What is CVE-2026-52870?

CVE-2026-52870 is a session isolation bypass in the MCP Python SDK's experimental task handlers. Connected clients could enumerate, read results from, and cancel other clients' tasks because task operations did not validate session ownership, allowing privilege escalation within multi-client MCP deployments.

Is CVE-2026-52870 being actively exploited?

No, CVE-2026-52870 is not listed on the CISA Known Exploited Vulnerabilities (KEV) catalog and no public exploits are currently available. However, the vulnerability poses a significant risk in production environments with multiple concurrent MCP clients.

What versions of the MCP Python SDK are affected by CVE-2026-52870?

MCP SDK versions 1.23.0 through 1.27.1 are vulnerable. Version 1.27.2 and later contain the remediation and enforce proper session-based task isolation.

How do I check if my server is vulnerable to CVE-2026-52870?

Run 'pip3 show mcp | grep Version' to check the installed version. If the version is between 1.23.0 and 1.27.1 inclusive, and your configuration includes server.experimental.enable_tasks(), your deployment is vulnerable.

Does Defensia detect CVE-2026-52870?

Yes — Defensia's CVE advisory scanner compares installed package versions against the NVD database. If the MCP Python SDK is installed on a monitored server, CVE-2026-52870 will appear in your dashboard with remediation steps.

Related Python CVEs

CVE-2026-25632CVSS 10EPyT-Flow is a Python package designed for the easy generation of hydraulic and water quality scenario data of water distribution networks. Prior to 0.16.1, EPyT-Flow’s REST API parses attacker-controlled JSON request bodies using a custom deserializer (my_load_from_json) that supports a type field. When type is present, the deserializer dynamically imports an attacker-specified module/class and instantiates it with attacker-supplied arguments. This allows invoking dangerous classes such as subprocess.Popen, which can lead to OS command execution during JSON parsing. This also affects the loading of JSON files. This vulnerability is fixed in 0.16.1.
CVE-2026-33054CVSS 10Mesop is a Python-based UI framework that allows users to build web applications. Versions 1.2.2 and below contain a Path Traversal vulnerability that allows any user supplying an untrusted state_token through the UI stream payload to arbitrarily target files on the disk under the standard file-based runtime backend. This can result in application denial of service (via crash loops when reading non-msgpack target files as configurations), or arbitrary file manipulation. This vulnerability heavily exposes systems hosted utilizing FileStateSessionBackend. Unauthorized malicious actors could interact with arbitrary payloads overwriting or explicitly removing underlying service resources natively outside the application bounds. This issue has been fixed in version 1.2.3.
CVE-2026-34938CVSS 10PraisonAI is a multi-agent teams system. Prior to version 1.5.90, execute_code() in praisonai-agents runs attacker-controlled Python inside a three-layer sandbox that can be fully bypassed by passing a str subclass with an overridden startswith() method to the _safe_getattr wrapper, achieving arbitrary OS command execution on the host. This issue has been patched in version 1.5.90.
CVE-2026-28505CVSS 10Tautulli is a Python based monitoring and tracking tool for Plex Media Server. Prior to version 2.17.0, the str_eval() function in notification_handler.py implements a sandboxed eval() for notification text templates. The sandbox attempts to restrict callable names by inspecting code.co_names of the compiled code object. However, co_names only contains names from the outer code object. When a lambda expression is used, it creates a nested code object whose attribute accesses are stored in code.co_consts, NOT in code.co_names. The sandbox never inspects nested code objects. This issue has been patched in version 2.17.0.
CVE-2026-25115CVSS 9.9n8n is an open source workflow automation platform. Prior to version 2.4.8, a vulnerability in the Python Code node allows authenticated users to break out of the Python sandbox environment and execute code outside the intended security boundary. This issue has been patched in version 2.4.8.

References

Track CVEs across your fleet automatically

Defensia scans your Linux servers and tells you exactly which ones are running vulnerable versions — including CVE-2026-52870. Free for 1 server.

Get started free