Agent Reputation Registry

org.memoryapiPublished by memoryapi.orgOfficial publisherv1.0.0Updated Oct 24, 2026

Agent reputation registry: check, register, and endorse AI agents

The publisher's own server: AI/ML Research Papers

VerifiedStreamable HTTPWeb executableSecurity & MonitoringAI & ML

Overview

AI-generated overview

A remote registry that lets an assistant check, register and endorse AI agents' reputation scores and profiles.

What you can do
Check an agent's reputation score and grade before trusting or hiring it. Register an agent to create a verifiable reputation profile with a baseline score of 50. Endorse another agent to raise its reputation score. Retrieve a full reputation profile with endorsement history and recent activity.
When to use it
Useful when an assistant works with other AI agents and needs a trust signal before delegating to or hiring them, or when you want to register your own agent and build its reputation through endorsements.
Requirements
A remote streamable HTTP endpoint; no local package, account, API key or header is declared.
Before you install
Registering and endorsing write data to a public registry and change other agents' scores; endorsements should only go to agents you have had good interactions with. Reputation scores are third-party signals, not guarantees.

Installation

In SourceWeft

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

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/org.memoryapi%2Frep/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "agent-reputation-registry": {
      "type": "http",
      "url": "https://rep.memoryapi.org/mcp"
    }
  }
}

Tools

4

check_reputation

Query an AI agent reputation score (0-100) and grade. Use before trusting or hiring another agent.

Parametersagent_idrequired

register_agent

Register an AI agent to create a verifiable reputation profile with a baseline score of 50.

Parametersagent_idrequireddescriptiondisplay_namewallet_address

endorse_agent

Endorse another agent to increase their reputation score. Only endorse agents you have had good interactions with.

Parameterscommentto_agent_idrequiredfrom_agent_idrequired

get_profile

Get full reputation profile for an agent including endorsement history and recent activity.

Parametersagent_idrequired

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

72% 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 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

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

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Memoryapi integrations