openrhyme-mcp
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@openrhyme-mcp show my activity from the last two hours"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
openrhyme-mcp
A thin Model Context Protocol server that exposes the timeline captured by the OpenRhyme engine to any agent — Claude, local models, your own scripts — over stdio.
Status: MVP implemented on this branch — a stdio MCP server exposing the engine's raw event timeline and app-allowlist controls, tested against a fixture store and a fake engine binary. The engine it depends on (OpenRhyme/OpenRhyme) has its Part 1 (capture) complete. Pending: dogfooding against a live engine capture; richer retrieval (sessions, search, embeddings) is future work.
What it is, and is not
OpenRhyme is a local-first, open-source "Computer History" for macOS: a Swift daemon reads your activity through the accessibility API, stores it in tiered SQLite, and compacts it without any bundled model. This repository is the agent-facing door to that data. It:
speaks MCP over stdio, so any agent host (Claude Desktop, Claude Code, …) can spawn it;
reads the engine's SQLite tiers read-only;
shells out to the
openrhymeCLI (openrhyme <cmd> --json) for control commands;contains no capture logic, holds no macOS permissions, and makes no network calls.
Everything stays on your machine. The agent host that spawns this server is the trust boundary — it sees exactly what the tools return, nothing more.
Related MCP server: Rob Desktop Commander
How the pieces fit
openrhyme daemon (Swift, launchd) ──writes──▶ ~/Library/Application Support/OpenRhyme/*.sqlite
│
read-only │ `openrhyme … --json`
▼ │
agent host ──stdio──▶ openrhyme-mcp (this repo) ─────┘The full process topology, the CLI/JSON contract, and the store layout are specified in the engine repo: docs/engine-interface.md. That document is the contract this server implements; it is not duplicated here.
Tools & resources
MCP tool | Returns |
| raw events in a time window: |
| engine trust/daemon/store status, plus this server's schema and db info |
| the capture allowlist and currently running apps |
| add/remove an app from the capture allowlist, by bundle identifier |
MCP resource | Contents |
| the last 15 minutes of raw events, as JSON Lines |
Richer retrieval (sessions, full-text search, embeddings) is future work, not yet built.
Development
Requires Python 3.12+ and uv.
make sync # uv sync --all-groups
make check # ruff + mypy (strict) + pytest
uv run openrhyme-mcp # serve on stdio (Ctrl-C to stop)Tests run in-process against a fixture database and a fake openrhyme script; they never need the real engine or a macOS permission. CI runs on Ubuntu and macOS 26.
Using it with an agent
With the engine built (../OpenRhyme, make build) and on PATH — or pointed to via OPENRHYME_BIN:
claude mcp add openrhyme -- uv run --directory /path/to/openrhyme-mcp openrhyme-mcpThen ask: "What was I doing between 2 and 3 pm?" — the model calls events(since="…", until="…"). Tools: events, status, apps, allow_app, deny_app; resource: openrhyme://events/recent. Environment: OPENRHYME_DATA_DIR (engine data dir), OPENRHYME_BIN (engine binary).
License
MIT — see LICENSE.
Available Tools
5 toolsallow_appA
Add an app to the capture allowlist by bundle identifier (e.g. com.apple.Safari). Takes effect within a few seconds; the daemon reloads its config on each heartbeat.
Inputs: bundle_id (required). Returns: object
appsC
The capture allowlist and the currently running apps (with bundle identifiers, whether each is allowlisted, and whether it is an Electron app).
Inputs: no named parameters. Returns: object
deny_appA
Remove an app from the capture allowlist by bundle identifier.
Inputs: bundle_id (required). Returns: object
eventsA
Raw activity events between since and until, oldest first.
Returns {"events": [...rows...], "count": N}; each row's keys are the event columns (bundle_id, app_name, window_title, kind, value, ...) and a local-ISO "time" field. Read result["events"] for the rows.
Times accept 2h / 30m / 1d (that long ago), unix seconds, or ISO-8601.
kinds filters by event kind (e.g. app.activated, window.focused,
context.snapshot, element.value_changed); app by bundle identifier.
value/selected_text are cut to max_value_chars (0 = full text). limit ≤ 2000.
Inputs: since (required), app, kinds, limit, +2 more. Returns: object
statusA
Engine status (trust, daemon liveness, event count, allowlist) plus this server's view: supported schema, database path and whether it exists.
Inputs: no named parameters. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a clearly distinct role: events queries captured activity data, status reports engine/server state, apps lists the allowlist and running apps, and allow_app/deny_app make targeted allowlist changes. There is no functional overlap between any of these tools.
The read-only tools use noun-style names (events, status, apps) while the mutations use verb_noun style (allow_app, deny_app). This is fairly predictable and readable, though not as uniform as a single verb_noun convention throughout.
Five tools is well-scoped for this server's purpose: querying activity events, checking engine status, listing apps, and managing the allowlist. Each tool earns its place without the surface feeling bloated or thin.
The core workflows are fully covered: retrieve activity data, inspect engine health, view the allowlist, and add or remove apps from it. Since events are an append-only raw log, update/delete operations are not expected here, so there are no obvious gaps.
Maintenance
Related MCP Connectors
Persistent memory, hybrid search and a goal graph for AI agents, over stdio or remote HTTP.
Search your AI chat history (ChatGPT, Claude, Codex) from any MCP client. Remote, private, read-only
Agent-native MCP server over the public saagarpatel.dev corpus. Read-only, stateless.
Remote MCP server exposing your Node Command fleet (files, shell, processes, browser) to AI hosts.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides a stdio MCP bridge for coding agents to query and record engineering knowledge locally, preserving debugging history, failed attempts, and verified solutions.MIT
- AlicenseAqualityBmaintenanceEnables MCP-capable AI clients to control a local computer over stdio with filesystem operations, ripgrep search, shell command execution, and persistent process sessions.14MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to search, record, correct, and review the provenance and version history of memories, and to obtain answers composed from guarded context in which private values are replaced by placeholders and resolved locally on the device. Exposes these capabilities through dependency-free tools over stdio.MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP stdio bridge that lets compatible agents query a local, provenance-first memory graph, fetch source-versioned text, inspect retrieval, check service health, and report usefulness feedback.1MIT