Agents in the Wild

co.agentsinthewildPublished by agentsinthewild.coOfficial publisherv1.0.0Updated Nov 4, 2026

Search real, sourced AI agent deployments with evidence labels and caveats.

VerifiedStreamable HTTPWeb executableKnowledge & MemoryData & Analytics

Overview

AI-generated overview

Read-only directory of real, sourced AI agent deployments, letting an assistant search use cases and pull evidence labels, caveats and sources.

What you can do
  • Search real AI agent deployments at named organizations, with reported outcomes and evidence labels
  • Read a full entry by slug: summary, outcome, metrics, evidence label, caveats and source links
  • Get dataset-wide statistics: evidence mix, share self-reported, categories, industries, top tools and years
When to use it
Useful when you need concrete, attributable examples of AI agent deployments for research, comparison, or citing in a write-up, and want to see who made each claim and what caveats apply.
Requirements
Remote streamable HTTP endpoint at agentsinthewild.co; no packages, environment variables or headers declared. Network access required.
Before you install
Entries are claims with evidence labels, not verified facts; some are self-reported. Check the caveats and source links before quoting, and attribute results to the reporting party.

Installation

In SourceWeft

  1. Open Agents in the Wild 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/co.agentsinthewild%2Fagents-in-the-wild/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": {
    "agents-in-the-wild": {
      "type": "http",
      "url": "https://agentsinthewild.co/mcp"
    }
  }
}

Tools

3

search_use_cases

Search AI agent deployments

Search real, sourced AI agent deployments at named organizations. Each result has the reported outcome and an evidence label saying who made the claim. Call get_use_case for sources and caveats before quoting a result.

Parameterstoollimitquerycategoryevidenceindustry

get_use_case

Get one AI agent deployment

Full entry by slug: summary, outcome, metrics, evidence label, caveats, and source links.

Parametersslugrequired

get_dataset_stats

State of AI agents in production

Statistics over all entries: evidence mix, share self-reported, categories, industries, top tools, and years.

Takes no parameters.

Version history

1
  1. v1.0.0LatestNov 4, 2026

Score

83% 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
  • 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.