Search real, sourced AI agent deployments with evidence labels and caveats.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Statistics over all entries: evidence mix, share self-reported, categories, industries, top tools, and years.
This tool takes no arguments.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http agents-in-the-wild https://agentsinthewild.co/mcp
Statistics over all entries: evidence mix, share self-reported, categories, industries, top tools, and years.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Full entry by slug: summary, outcome, metrics, evidence label, caveats, and source links.
| Argument | Type | Description |
|---|---|---|
| slug* | string | Slug from search_use_cases, e.g. 'stripe-minions-coding-agents'. |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "Slug from search_use_cases, e.g. 'stripe-minions-coding-agents'."
}
},
"additionalProperties": false
}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.
| Argument | Type | Description |
|---|---|---|
| tool | string | Agent framework, model, or product name, e.g. 'Claude Code' or 'Devin'. |
| limit | integer | |
| query | string | Words to match, e.g. 'customer support refunds' or 'code migration'. |
| category | string | |
| evidence | string | Only results with this evidence label. |
| industry | string |
{
"type": "object",
"properties": {
"tool": {
"type": "string",
"description": "Agent framework, model, or product name, e.g. 'Claude Code' or 'Devin'."
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 25,
"minimum": 1
},
"query": {
"type": "string",
"description": "Words to match, e.g. 'customer support refunds' or 'code migration'."
},
"category": {
"enum": [
"customer-support",
"software-engineering",
"security",
"sales-marketing",
"finance-operations",
"data-analytics",
"research",
"legal",
"healthcare",
"hr-recruiting",
"internal-tools"
],
"type": "string"
},
"evidence": {
"enum": [
"vendor-case-study",
"company-reported",
"press-report",
"research-paper",
"independent"
],
"type": "string",
"description": "Only results with this evidence label."
},
"industry": {
"enum": [
"financial-services",
"software-and-cloud",
"retail-and-ecommerce",
"transport-and-travel",
"healthcare-and-life-sciences",
"security",
"media-and-entertainment",
"energy-and-utilities",
"professional-services"
],
"type": "string"
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 4, 2026.