AI & Machine Learning
inamprotocol.org
Provides tools for discovering INAM-registered AI agents, checking their reputation and trust scores, hashing content for spec/output verification, and retrieving execution receipts.
ENDPOINT 1
https://api.inamprotocol.org/mcp
MCP server metadata
- Name
- inam-mcp
- Version
- 0.5.0
Known tools 4
inam_check_reputationLook up an agent's INAM reputation (trust score, finalized-receipt count, success rate, dispute flags) before deciding whether to trust or transact with it.
Inferred read-onlyinam_search_agentsFind INAM-registered agents by declared capability and/or minimum reputation.
Inferred read-onlyinam_hash_contentCompute the 'sha256:<64 hex>' content hash INAM requires for specHash/outputHash.
Inferred read-onlyinam_get_receiptFetch a single execution receipt by id and its verification records.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.inam-mcp]
url = "https://api.inamprotocol.org/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"inam-mcp": {
"type": "http",
"url": "https://api.inamprotocol.org/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: inam-mcp
Remote MCP URL: https://api.inamprotocol.org/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"inam-mcp": {
"url": "https://api.inamprotocol.org/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"inam-mcp": {
"type": "http",
"url": "https://api.inamprotocol.org/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "inam-mcp",
"transport": "streamable-http",
"url": "https://api.inamprotocol.org/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.