MCP servers · actenon

Actenon Kernel: proof verifier for consequential AI actions

An open MCP verifier that checks a PCCB proof before a consequential action executes, refusing invalid attempts at the execution edge.

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

The Kernel is an open verifier that checks a PCCB (Proof of Constrained Capability Bound) before a consequential action runs. It confirms that the proof authorizes the exact action intent for this caller, target, audience, scope, time window and single execution attempt. If verification fails, the ProtectedExecutor at the execution edge refuses the attempt with no side effect and emits a structured Refusal; otherwise it emits a Receipt. The Kernel issues no grants and makes no policy decisions, which belong to the separate Permit component.

It suits developers who need to close the gap between upstream authorization and the moment an action executes, where parameters can change after approval, a valid-looking proof can be replayed, or a stale proof can be reused. It can be wired in at the agent framework, for example as a LangChain or MCP tool, or at the resource boundary, such as a FastAPI, Express or Go HTTP route. A Python reference is provided, along with TypeScript, Go and Rust verifier SDKs that conform to the same 53 conformance vectors.

The Python package depends only on actenon-protocol. Verification makes no network calls and works without Permit, Cloud or Scan. The conformance vectors can be run with the kernel's conformance command, and the full scope and guarantees are documented in the repository.

Limitations and requirements

The edge guarantee holds only when the protected edge is the only path to the resource, the backend accepts only brokered credentials issued after verification, and the agent has no standing credential or alternate route. If these conditions are not met, invalid proofs are still refused, but a caller that bypasses the Kernel can still reach the resource. Actenon Cloud is an optional private repository that is not publicly available.

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
    Actenon Kernel

    Verify consequential AI actions before they execute.

    v1.2.2
    As shown on registry.modelcontextprotocol.io when we last read it
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
MCP servers
neondatabase

Neon MCP Server (Postgres)

Neon's MCP server for managing Neon Postgres in plain language: create projects and branches, run queries and prepare schema migrations from your editor.

663 GitHub starsData & databasesSoftware 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
supabase-community

Supabase MCP Server

Supabase's MCP server that connects an AI assistant to your Supabase project to design tables, run queries, read configuration and look up documentation.

Data & databasesSoftware development
Updated 17 Nov 2026