// Use the Hive MCP server for the thin v2 search and execute tool surface. Use this skill when configuring MCP access to Hive or when an agent needs workspace search and bounded local execution.
| name | hive-mcp |
| description | Use the Hive MCP server for the thin v2 search and execute tool surface. Use this skill when configuring MCP access to Hive or when an agent needs workspace search and bounded local execution. |
The MCP surface is intentionally small — two tools for agent integration:
search — query workspace stateexecute — run bounded Python codeEverything durable still goes through the hive CLI and the .hive/ substrate.
Example MCP config:
{
"mcpServers": {
"hive": {
"command": "hive-mcp",
"env": {
"HIVE_BASE_PATH": "/path/to/workspace"
}
}
}
}
HIVE_BASE_PATH should point at the workspace you want the server to search and execute against.
If running from a local checkout instead of an installed package, uv run hive-mcp is the equivalent launch command.
searchSearch workspace state, API docs, examples, schemas, and project summaries.
Arguments:
query requiredscopes optional — filter to specific indexes (api, examples, project, workspace)limit optional, defaults to 8Example:
{
"name": "search",
"arguments": {
"query": "run acceptance",
"scopes": ["api", "workspace"],
"limit": 5
}
}
executeRun bounded local code with a typed Hive client.
Arguments:
code requiredlanguage optional, Python only for nowprofile optionaltimeout_seconds optionalExample:
{
"name": "execute",
"arguments": {
"language": "python",
"profile": "default",
"code": "result = hive.task.ready(limit=3)"
}
}
execute is intentionally bounded and time-limitedUse the CLI for:
Use MCP when an agent needs fast search or a local execution sandbox inside a host application.
Discipline for developing Hive itself — PR sizing, review handling, merge discipline, release workflow, delegation, and cleanup hygiene. Use this skill when working on Hive repo changes that span multiple PRs or review cycles.
Coordinate work across multiple agents and projects in Hive. Covers task claims, blockers, handoffs, campaigns, portfolio management, briefs, and shared memory.
Hive mental model and orientation. Read this first before using any other Hive skill. Covers the entity hierarchy, observe-and-steer pattern, drivers, sandboxes, console vs CLI, and workspace conventions.
Set up and configure Hive workspaces, projects, tasks, and evaluator policy. Use this skill when bootstrapping, creating projects, managing tasks, or configuring PROGRAM.md.
The core agent work cycle in Hive — from finding a task through claiming, launching a run, handling approvals, finishing, and promoting. Use this skill for task-first project work, governed runs, and clean handoff.