AgentWatchr

com.agentwatchrPublished by agentwatchr.comOfficial publisherv0.2.1Updated Oct 27, 2026

Read-only agent identity index with provenance, historical evidence and explained coverage.

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

Read-only index of observed agent source identities, with profiles, evidence scores, coverage stats and bounded network analyses.

What you can do
  • Search observed source identities in the agent index
  • Read an identity's profile, supporting evidence and explained Evidence Score
  • Read evidence and coverage distributions across the index
  • Read bounded network analyses labelled FACT, INTERPRETATION or CONFIDENCE
When to use it
Useful when you need to look up an agent or source identity and see what evidence backs it, how well it is covered, and how it relates to others, without any write access.
Requirements
A remote streamable HTTP endpoint at agentwatchr.com; no packages, environment variables or headers are declared, and no authentication is declared.
Before you install
Results describe observed source identities, not verified real-world agents, so treat profiles and scores as evidence-based signals rather than confirmation. Insights mix fact, interpretation and confidence, so check which label applies before relying on a claim.

Installation

In SourceWeft

  1. Open AgentWatchr 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/com.agentwatchr%2Fevidence-index/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": {
    "agentwatchr": {
      "type": "http",
      "url": "https://agentwatchr.com/mcp"
    }
  }
}

Tools

4

search_agents

Search observed source identities, not verified real-world agents.

Parametersquerysource

get_agent

Read profile, evidence and explained Evidence Score.

Parametersidrequired

get_stats

Read evidence and coverage distributions.

Takes no parameters.

get_insights

Read bounded FACT / INTERPRETATION / CONFIDENCE network analyses.

Parameterssection

Version history

1
  1. v0.2.1LatestOct 26, 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.