
Hermai Mcp
Connects Claude to the Hermai platform for schema discovery and workflow intake. You get five tools: lookup and list public schemas by domain or task, submit six-field intake forms for brittle browser or API workflows, classify whether a workflow needs direct API calls versus browser automation, and check request status. Public schema lookup and request submission work without authentication, though you can pass HERMAI_API_KEY for authenticated endpoints. Run it with npx or install globally. Useful when you're building agents that need to discover existing automation schemas or route new workflow requests into Hermai's system without switching to the CLI.
- tools
- 6
- transport
- STDIO
- last updated
- May 24, 2026
Tools
6 toolsPublic tool metadata for what this MCP can expose to an agent.
lookup_schemaSearch Hermai schemas by domain, task, category, or verification state.
Search Hermai schemas by domain, task, category, or verification state.
No parameter schema in public metadata yet.
list_public_schemasPage through public schemas.
Page through public schemas.
No parameter schema in public metadata yet.
submit_schema_requestSubmit the six-field intake for a brittle browser/API workflow.
Submit the six-field intake for a brittle browser/API workflow.
No parameter schema in public metadata yet.
classify_browser_workflowLocally classify whether a workflow maps to direct API, hidden endpoint, browser-only, or owner/auth work.
Locally classify whether a workflow maps to direct API, hidden endpoint, browser-only, or owner/auth work.
No parameter schema in public metadata yet.
check_schema_request_statusCheck a schema request status.
Check a schema request status.
No parameter schema in public metadata yet.
fetch_schemaExecute a registered schema through hosted /v1/fetch and return live data.
Execute a registered schema through hosted /v1/fetch and return live data.
No parameter schema in public metadata yet.
Sponsors
Readme
Hermai MCP
Dedicated Model Context Protocol server for Hermai.
Use this package when an agent runtime supports MCP and should call Hermai as native tools. The Hermai CLI is a separate human/operator tool and is not required for MCP.
Install
Run directly with npx:
npx -y hermai-mcp
Or install globally:
npm install -g hermai-mcp
hermai-mcp
MCP Client Config
{
"mcpServers": {
"hermai": {
"command": "npx",
"args": ["-y", "hermai-mcp"]
}
}
}
Optional environment variables:
HERMAI_API_BASEorHERMAI_PLATFORM_URL: API base URL. Defaults tohttps://api.hermai.ai.HERMAI_API_KEYorHERMAI_PLATFORM_KEY: API key for authenticated Hermai APIs. Public schema lookup and schema-request intake work without a key. Setting a key also unlocks thefetch_schemaexecution tool (see below).HERMAI_FETCH_TIMEOUT_MS: request timeout forfetch_schema. Defaults to120000(hosted fetch lanes can run tens of seconds).
Claude Code workflow
Details
- Repository
- github.com/hermai-ai/hermai-mcp
- Category
- Automation & Workflows
- Package
hermai-mcp- Transport
- STDIO
- Registry
- MCP registry, active