Positif

ai.positifPublished by positif.aiv0.2.2Updated Oct 30, 2026

The agent switchboard: identity, policy, loop-guard, and an append-only audit ledger.

VerifiedSTDIODesktop onlySecurity & MonitoringAI & ML

Overview

AI-generated overview

Positif is a local agent switchboard MCP server that adds identity, policy, loop-guard and an append-only audit ledger to an assistant's tool use.

What you can do
  • Provides an agent switchboard layer around an assistant's activity.
  • Covers identity and policy for agent actions.
  • Includes loop-guard to limit repeated agent cycles.
  • Records activity in an append-only audit ledger.
  • No individual tools are listed, so exact operations are not documented in the supplied material.
When to use it
Worth considering when you want oversight of an AI agent's actions: who acted, under what policy, with repeated loops stopped and a tamper-evident record kept. Best suited to desktop setups where the agent runs locally.
Requirements
Runs as a local process over stdio, installed from the PyPI or npm package positif-ai; desktop only, not web-executable. No authentication, environment variables or headers are declared.
Before you install
The audit ledger is described as append-only, so expect records of agent activity to be retained. Identity and policy handling means the server mediates agent actions; review how those policies are configured before relying on it. No tools, configuration or data-handling details are documented in the supplied material.

Installation

In SourceWeft

  1. Open Positif in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.2.2LatestSep 16, 2026

Score

25% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.