Pathrule
OfficialPathrule Remote MCP lets AI coding agents read and write path-scoped project context (memories, rules, skills, snapshots, and activity logs) stored in Pathrule cloud workspaces via the Model Context Protocol — no local installation required.
Workspace & Context
List organizations and workspaces, create new workspaces, and run a bootstrap/setup flow to seed project context
Get path-scoped context (memories, rules, skills, subtree index) for any workspace path
Navigate the workspace tree with fuzzy path/name resolution, browse the full node tree, and inspect individual nodes
Ping the server to verify connectivity
Memories
List, read, create, update, and delete memories attached to workspace paths
Supports soft/hard delete, optimistic concurrency (
expected_version_id), and linking to multiple paths
Rules
List, read, create, update, and delete path-scoped rules
Assign scope types and priority levels (
high,medium,low); optimistic concurrency supported
Skills
List, read, create, update, and delete skills (SKILL.md format with frontmatter + markdown)
Supports manual, template, and GitHub-referenced sources; tag skills and link to GitHub URLs
Snapshots
Take point-in-time project snapshots (file tree, sampled contents, git info, AI observations)
List and read existing snapshots
Refresh Tasks
List pending memory/rule refresh tasks, claim and read their briefs, and resolve them as applied or rejected
Activity Logging
Log file-modifying actions from AI agents, categorized by domain, action, scope, and files touched
Upgrade Guidance
Get information on what Pathrule CLI/Desktop unlock beyond Remote MCP (hooks, local file access, automatic AGENTS.md/CLAUDE.md rendering, on-disk skill materialization, etc.)
Pathrule Remote MCP
Pathrule Remote MCP exposes Pathrule workspace memory, rules, skills, setup, snapshots, and activity logging over the Model Context Protocol.
Public endpoint:
https://mcp.pathrule.io/mcpRegistry manifest:
https://mcp.pathrule.io/server.jsonWhat It Does
Pathrule gives AI coding agents path-scoped project context. The remote MCP server lets cloud MCP clients use the same Pathrule workspace data without installing Pathrule Desktop or the local CLI on the client host.
Remote MCP is intentionally cloud-only. It can read and write Pathrule cloud records, but it cannot read local files, install hooks, render AGENTS.md / CLAUDE.md, or materialize local skills. For those local runtime features, use Pathrule Desktop or @pathrule/cli.
Using Pathrule Remote MCP
Pathrule Remote MCP is the MCP endpoint for Pathrule Web workspaces. It is not a general-purpose hosted memory service that works without Pathrule.
To use it:
Create or sign in to a Pathrule account:
https://app.pathrule.ioCreate or select a Pathrule workspace in the app.
Connect your MCP client to:
https://mcp.pathrule.io/mcpWhen an MCP client connects, it starts an OAuth flow through Pathrule Web. After approval, the client can access only the Pathrule workspaces visible to that signed-in account, using the scopes you approved.
This repository is the public source and directory listing target for Pathrule's Remote MCP endpoint. It is not a standalone local memory database, and it does not create a usable Pathrule workspace without a Pathrule account.
Tools
Workspace and context:
pathrule_list_workspacespathrule_get_contextpathrule_gotopathrule_get_treepathrule_get_nodepathrule_list_memoriespathrule_read_memorypathrule_read_rulepathrule_read_skillpathrule_ping
Workspace setup:
pathrule_list_organizationspathrule_create_workspacepathrule_setup
Writes:
pathrule_write_memorypathrule_update_memorypathrule_delete_memorypathrule_write_rulepathrule_update_rulepathrule_delete_rulepathrule_write_skillpathrule_update_skillpathrule_delete_skill
Snapshots, refreshes, and activity:
pathrule_take_snapshotpathrule_list_snapshotspathrule_read_snapshotpathrule_list_pending_refreshespathrule_get_refresh_briefpathrule_resolve_refreshpathrule_log_activitypathrule_get_local_runtime_upgrade
Security Model
OAuth scopes decide the tool surface. Read tools require
pathrule:read; write tools requirepathrule:write; refresh/activity tools requirepathrule:activity.Every workspace operation runs through the authenticated user's Supabase JWT and database RLS policies.
The connector does not use Supabase admin keys to widen user access.
Write tools are also gated by workspace subscription status and per-user/per-workspace rate limits.
MCP event telemetry is metadata-only: tool name, user/workspace/client identifiers, status/error code, and latency bucket. Tool input and content bodies are not logged.
The remote server never accesses the user's filesystem and never writes local companion files.
Operator Notes
The mcp.pathrule.io service is operated by Pathrule. The environment variables below are for Pathrule operators deploying the service against Pathrule's backend. They are not required to connect an MCP client to Pathrule Remote MCP.
Required production secrets are environment variables only. Do not commit values for:
SUPABASE_URL
SUPABASE_ANON_KEY
SUPABASE_JWT_SECRET
PATHRULE_CONNECTOR_TOKEN_ENCRYPTION_KEY
PATHRULE_CONNECTOR_TOKEN_ENCRYPTION_KEY_VERSION
PATHRULE_CONNECTOR_TOKEN_ENCRYPTION_PREVIOUS_KEYS
PATHRULE_WEB_ORIGINSUPABASE_JWT_SECRET is used to sign short-lived authenticated-role user JWTs for Supabase RLS. Treat it like production infrastructure secret material and store it only in the hosting provider's secret manager.
Running The Server
The public pathrule/mcp repository is staged from the Pathrule monorepo and contains a bundled Node.js server for transparency and deployment reproducibility. Running it yourself requires the environment variables above and Pathrule's compatible backend; it is not the recommended user setup path.
npm install
npm startThe server listens on PORT and HOST:
PORT=8787
HOST=0.0.0.0Health and metadata:
curl -fsS http://localhost:8787/healthz
curl -fsS http://localhost:8787/server.jsonRegistry Inspection
The public repository includes a Dockerfile for MCP registry scanners such as Glama. The container sets PATHRULE_MCP_PUBLIC_INTROSPECTION=1, which exposes MCP schema introspection without a bearer token so registries can verify the server shape.
That mode does not grant Pathrule data access. Tool calls still require an authenticated Pathrule context and return auth errors without OAuth.
Glama's Docker build runner launches MCP servers through stdio. Use this command in Glama's Dockerfile admin form:
["node", "dist/glama-stdio.js"]MCP Directory Submission
Use these fields for MCP directories:
GitHub Repository URL: https://github.com/pathrule/mcp
npm Package: leave blank unless @pathrule/mcp is published
Short Description: Path-scoped team memories, rules and skills for AI coding agents.
Server URL: https://mcp.pathrule.io/mcpLicense
MIT
Maintenance
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/pathrule/mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server