Skip to main content

Orcho — Model Context Protocol server for Claude Code, Cursor, Zed, and other MCP-speaking clients

Project description

orcho-mcp

PyPI Python 3.12+ License: Apache-2.0 CI DCO Release codecov OpenSSF Scorecard

Model Context Protocol server for Orcho.

Exposes orcho's runtime to MCP-aware clients (Claude Code, Cursor, Zed, and other MCP-speaking tools) over stdio. Full async control loop — act, observe, decide, inspect — without raw log scraping.

Status: v0.1.0 public release line. Core control loop surfaces are available:

  • Act: orcho_run_start / orcho_run_resume / orcho_run_cancel with L4-test-pinned semantics (process-group signal handling, supervisor-owned restart-recovery, race-aware cancel).
  • Observe: orcho_run_status / orcho_run_history / orcho_run_metrics / orcho_run_events_tail — read-only, polling-friendly.
  • Decide: orcho_phase_handoff_decide — generic phase-handoff state transition for paused runs. The pipeline pauses with status=awaiting_phase_handoff when a phase's declared handoff policy fires; continue / retry_feedback / halt write a decision artifact (halt flips meta.status to halted synchronously). Pure state transition; never spawns.
  • Inspect: orcho_run_evidence — typed inspection slices (plan / findings / commands / artifacts / errors / sub_runs / all) with severity filter (P0..P3).

Live progress: orcho_run_watch emits ordered notifications/progress when the MCP request carries a progressToken. Clients that don't carry one poll orcho_run_status / orcho_run_events_tail against the same run state.

Install

pipx install 'orcho[mcp]'

For a project-managed Python environment:

pip install orcho-mcp

This pulls orcho-core (the engine), the official mcp Python SDK, and the runtime pieces orcho-mcp depends on.

Create a workspace

Orcho writes run state into an Orcho workspace. Start by pointing it at the folder that groups your project repos:

orcho workspace init ~/www/my-workspace

The command creates ~/www/my-workspace/workspace-orchestrator/, including .orcho/ settings and extension-point guides, and prints the MCP config snippet for that workspace. To write the snippet directly into a project-local MCP config:

ORCHO_MCP_COMMAND="$(command -v orcho-mcp)"

orcho workspace init ~/www/my-workspace \
  --mcp-config ~/www/my-workspace/.mcp.json \
  --mcp-server-name orcho-my-workspace \
  --orcho-mcp-command "$ORCHO_MCP_COMMAND"

ORCHO_MCP_COMMAND must point to the command your MCP client can run. For packaged installs this is normally orcho-mcp. For source installs, use the absolute path inside the Orcho environment, for example /Users/me/orcho-preview/orcho-core/.venv/bin/orcho-mcp.

Each MCP server process owns one workspace through ORCHO_WORKSPACE. For multiple workspaces, add multiple MCP server entries.

Register with an MCP-aware client

Each client has its own MCP registry/config format. Use docs/mcp_client_setup.md for copy-paste instructions for Codex CLI/app, Claude Code, Gemini CLI, the Claude app, and Antigravity.

What's inside

npx @modelcontextprotocol/inspector orcho-mcp

Opens a web UI on localhost showing every registered tool, resource, and prompt with full JSON schemas — Anthropic's official Inspector ≈ Swagger UI for MCP.

A static catalogue is also committed at docs/mcp_schema.json — the same shape, snapshotted in CI.

Control loop

The full contract — starting, observing, resuming, cancelling, deciding (QA gate), and inspecting runs through the MCP wire — lives in docs/run_lifecycle.md. Tool docstrings stay terse; that file is the long-form reference.

Tool naming is consistent: every run-lifecycle tool is orcho_run_<verb>. State-transition and inspection tools sit beside that group with their own names:

Group Tools
Act orcho_run_start, orcho_run_resume, orcho_run_cancel
Observe orcho_run_status, orcho_run_history, orcho_run_metrics, orcho_run_events_tail
Decide orcho_phase_handoff_decide
Inspect orcho_run_evidence, orcho_run_diff

For an end-to-end walkthrough of the full control loop with code, see docs/control_loop_walkthrough.md.

Architecture

orcho-mcp is one of the public Orcho runtime packages:

  • orcho-core — pipeline runtime + CLI (Apache-2.0).
  • orcho-mcp — MCP server, this repo (Apache-2.0).

The post-v1 cross-MCP consumer roadmap (orcho-as-MCP-client — pipeline agents calling external GitHub / Linear / Slack MCP servers) is documented in orcho-core/docs/plans/2026-05-06-cross-mcp-orchestration.md.

For contributor-facing architecture and test guidance:

License

Apache-2.0. See LICENSE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

orcho_mcp-0.1.0.tar.gz (248.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

orcho_mcp-0.1.0-py3-none-any.whl (289.8 kB view details)

Uploaded Python 3

File details

Details for the file orcho_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: orcho_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 248.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for orcho_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 d9cd49b37dddfd0285128097e78ebb5620f55208a7bcb9aed591ee859ead4535
MD5 2430e05c7e3af5ffe0ebddea82715cf5
BLAKE2b-256 2205f250eebc22c9966b927282e37467289eed5f264f3103318b7ab3421b83b4

See more details on using hashes here.

Provenance

The following attestation bundles were made for orcho_mcp-0.1.0.tar.gz:

Publisher: release.yml on symphos-ai/orcho-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file orcho_mcp-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: orcho_mcp-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 289.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for orcho_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2e7ca5db0f19a2f607dc77223a0c98b4db560453981c1668a716af9ba7ab78ce
MD5 1ce5704f1cee6654039d12651039e3ac
BLAKE2b-256 68b482ca0a1697c1bd175336718c2a41a13052a4307e3f526c42965250c77126

See more details on using hashes here.

Provenance

The following attestation bundles were made for orcho_mcp-0.1.0-py3-none-any.whl:

Publisher: release.yml on symphos-ai/orcho-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page