MCP servers · ctrlrun

CTRLRun Operator

MCP server for listing, inspecting, granting or denying CTRLRun approval requests from an MCP client.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

CTRLRun is a Python library that checks each action an AI agent is about to take against a set of rules before the action runs. Allowed actions proceed, sensitive actions wait for a person, and forbidden actions are blocked. Operator is the MCP entry point for the approval step: from an MCP client, a person can list the actions currently held, inspect them, and grant or deny them.

It fits workflows where an agent can send, pay, refund, delete, deploy, grant, revoke, approve, submit, purchase or cancel, and where a human needs to decide on held requests without leaving their MCP client. The publisher states that every request, decision and result is recorded, refusals included. If an agent only reads and answers, the publisher says the library is not needed.

The library is installed from Python, and its rules live in a policy file, ctrlrun.yaml, with the protected call wrapped by a decorator. The publisher's description of this MCP entry does not give further setup details, such as how it connects to a running CTRLRun instance.

Limitations and requirements

The publisher states that CTRLRun does not detect prompt injection and cannot promise exactly-once execution against a remote system it does not control. It does not roll back actions. Receipts are not signed, and truncation or forged appends are not detected unless the head is anchored with 'ctrlrun anchor'. The publisher says its badge means only that declared guarantees pass in the tested setup, not that the system is secure, safe, compliant, certified or audited. The publisher also notes that OWASP-AGENTIC-TOP10.md lists four entries the library does not address.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    CTRLRun Operator

    Answer CTRLRun approvals from an MCP client: list what is held, inspect it, grant or deny.

    v0.12.2
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
cloudflare

Cloudflare MCP servers

Cloudflare's hosted MCP servers for its products: documentation search, sandbox containers, browser rendering, Radar internet data, logs and analytics, Workers and more.

4.5K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 17 Nov 2026
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026