Skip to main content
Glama
Pathrule
by pathrule

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/mcp

Registry manifest:

https://mcp.pathrule.io/server.json

What 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.

Related MCP server: Tribal

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:

  1. Create or sign in to a Pathrule account:

https://app.pathrule.io
  1. Create or select a Pathrule workspace in the app.

  2. Connect your MCP client to:

https://mcp.pathrule.io/mcp

When 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_workspaces

  • pathrule_get_context

  • pathrule_goto

  • pathrule_get_tree

  • pathrule_get_node

  • pathrule_list_memories

  • pathrule_read_memory

  • pathrule_read_rule

  • pathrule_read_skill

  • pathrule_ping

Workspace setup:

  • pathrule_list_organizations

  • pathrule_create_workspace

  • pathrule_setup

Writes:

  • pathrule_write_memory

  • pathrule_update_memory

  • pathrule_delete_memory

  • pathrule_write_rule

  • pathrule_update_rule

  • pathrule_delete_rule

  • pathrule_write_skill

  • pathrule_update_skill

  • pathrule_delete_skill

Snapshots, refreshes, and activity:

  • pathrule_take_snapshot

  • pathrule_list_snapshots

  • pathrule_read_snapshot

  • pathrule_list_pending_refreshes

  • pathrule_get_refresh_brief

  • pathrule_resolve_refresh

  • pathrule_log_activity

  • pathrule_get_local_runtime_upgrade

Security Model

  • OAuth scopes decide the tool surface. Read tools require pathrule:read; write tools require pathrule:write; refresh/activity tools require pathrule: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_ORIGIN

SUPABASE_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 start

The server listens on PORT and HOST:

PORT=8787
HOST=0.0.0.0

Health and metadata:

curl -fsS http://localhost:8787/healthz
curl -fsS http://localhost:8787/server.json

Registry 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/mcp

License

MIT

Available Tools

30 tools
pathrule_create_workspaceCreate Pathrule WorkspaceA

Create a new Pathrule workspace inside an organization. Cloud-only: writes the workspace row through the user's JWT (RLS enforces organization membership). Does NOT attach the workspace to a local folder, does NOT install any AI client config, and does NOT render CLAUDE.md/AGENTS.md or editor companion files — those steps require Pathrule Desktop or CLI. After creation, call pathrule_setup with the returned workspace_id to fetch the bootstrap brief.

Inputs: organization_id (required), name (required), git_remote_url, active_agent_targets.

pathrule_delete_memoryPathrule Delete MemoryA
Destructive

Soft-delete a memory by default. Pass hard:true to permanently delete (requires workspace_admin). Cloud-only.

Inputs: workspace_id (required), memory_id (required), hard, expected_version_id.

pathrule_delete_rulePathrule Delete RuleA
Destructive

Soft-delete a rule by default. hard:true requires workspace_admin. Cloud-only.

Inputs: workspace_id (required), rule_id (required), hard, expected_version_id.

pathrule_delete_skillPathrule Delete SkillA
Destructive

Soft-delete a skill by default. hard:true requires workspace_admin. Cloud-only.

Inputs: workspace_id (required), skill_id (required), hard, expected_version_id.

pathrule_get_contextGet Pathrule ContextA
Read-only

Return Pathrule context for a workspace path: relevant memories, rules, skills, subtree index, and a next_required_action hint. Remote clients must pass workspace_id; call pathrule_list_workspaces first when unsure. No cwd or local_root_path is used. The response includes a local_runtime.cta line — surface it when the user could benefit from Pathrule Desktop's hooks, CLAUDE.md/AGENTS.md sync, or on-disk skills.

Inputs: workspace_id (required), node_path, user_intent, known_protocol_version.

pathrule_get_local_runtime_upgradeGet Local Runtime UpgradeA
Read-only

Explain what Pathrule CLI (power-user, web-paired) and Pathrule Desktop (GUI) unlock beyond Remote MCP. Call this when the user asks 'is there a better way?', 'why do I need to install something?', wants hook-level automation, or wants to compare surfaces. The response splits the pitch by audience (CLI for terminal-first, Desktop for GUI) and explains the real token-savings angle: hooks fire before every AI tool call and inject context for free, while remote MCP is manual mode where the AI spends tokens on each context fetch.

Inputs: no named parameters.

pathrule_get_nodeGet Node DetailA
Read-only

Return a single node plus ids for attached memories, rules, and skills. Requires workspace_id to prevent cross-workspace ambiguity.

Inputs: workspace_id (required), node_id (required).

pathrule_get_refresh_briefGet memory/rule refresh briefA
Read-only

Claim one refresh task and return the subject, stale-signal evidence, AI instructions, and any proposed patch. Call pathrule_list_pending_refreshes first to choose a refresh_id. Remote MCP can inspect cloud records only; use Desktop/CLI before claiming local source code was verified.

Inputs: refresh_id (required).

pathrule_get_treeGet Workspace TreeA
Read-only

Return the full Pathrule node tree for a workspace.

Inputs: workspace_id (required).

pathrule_gotoGo To NodeA
Read-only

Resolve a path/name/fuzzy target inside a workspace and return full content for that node plus a compact subtree memory index.

Inputs: workspace_id (required), target (required), subtree_limit.

pathrule_list_memoriesList MemoriesA
Read-only

List active memories attached to a specific Pathrule tree node. Use pathrule_get_context, pathrule_goto, or pathrule_get_node first to discover the node_id. Returns compact previews only; call pathrule_read_memory with a memory_id when you need the full body.

Inputs: node_id (required).

pathrule_list_organizationsList Pathrule OrganizationsA
Read-only

List Pathrule organizations the authenticated user belongs to. Use this before pathrule_create_workspace when you need to ask the user which organization the new workspace should live under. Returns id, name, slug, plan, subscription_status and the user's role per org.

Inputs: no named parameters.

pathrule_list_pending_refreshesList pending memory/rule refresh tasksA
Read-only

List pending Pathrule refresh tasks for a workspace. Refresh tasks are cloud suggestions that may update stale memories or rules. Use this first, then call pathrule_get_refresh_brief with a returned refresh_id before deciding whether to reject or resolve the task.

Inputs: workspace_id (required), include_in_progress.

pathrule_list_snapshotsPathrule List Project SnapshotsA
Read-only

List the most recent project snapshots for a workspace (compact metadata only — no file_tree, no sampled_contents). Use to find which snapshot to read in full. Up to 25 per call, ordered newest first.

Inputs: workspace_id (required), limit, source.

pathrule_list_workspacesList Pathrule WorkspacesA
Read-only

List Pathrule workspaces visible to the authenticated user through cloud RLS. Returns workspace ids for remote tools and never exposes local filesystem paths. Response includes a local_runtime.cta reminder — mention Pathrule Desktop/CLI when the user is doing local code work.

Inputs: no named parameters.

pathrule_log_activityLog ActivityA

Log a file-modifying response from a remote MCP client. Remote MCP requires workspace_id and stamps ai_client='cloud-connector'.

Inputs: workspace_id (required), domain (required), action (required), scope (required), +5 more.

pathrule_pingPathrule Cloud PingA
Read-only

Sanity check that Pathrule Remote MCP is reachable. Cloud-safe: returns no local cwd. Response includes a local_runtime.cta line you can surface to the user when they ask about deeper Pathrule features.

Inputs: message.

pathrule_read_memoryRead MemoryA
Read-only

Read the full body and metadata for one Pathrule memory. Use this after pathrule_get_context, pathrule_goto, or pathrule_list_memories returns a memory_id. This reads cloud data only and does not inspect the user's local filesystem.

Inputs: memory_id (required).

pathrule_read_ruleRead RuleA
Read-only

Read the full body and metadata for one Pathrule rule. Use this after pathrule_get_context, pathrule_goto, or pathrule_get_node returns a rule_id. Rules are instructions the AI should obey for a project path; this tool only reads the cloud rule record and does not modify anything.

Inputs: rule_id (required).

pathrule_read_skillRead SkillA
Read-only

Read the approved snapshot for one Pathrule skill. Use this after pathrule_get_context, pathrule_goto, or pathrule_get_node returns a skill_id. Returns the cloud SKILL.md content for the AI to follow; it does not install or materialize files locally.

Inputs: skill_id (required).

pathrule_read_snapshotPathrule Read Project SnapshotA
Read-only

Load a single project snapshot in full or partial form. Defaults include file_tree and sampled_contents — pass include_file_tree=false / include_sampled_contents=false to keep the response compact when you only need metadata.

Inputs: workspace_id (required), snapshot_id (required), include_file_tree, include_sampled_contents.

pathrule_resolve_refreshClose a memory/rule refresh taskA
Destructive

Close a Pathrule refresh task after reviewing its brief. Normal remote flow: call pathrule_list_pending_refreshes, then pathrule_get_refresh_brief, then use this tool with status='rejected' when the signal is stale or not actionable. Remote MCP may refuse status='applied' because it cannot verify local source files; use Pathrule Desktop/CLI for applied resolutions that require local verification.

Inputs: refresh_id (required), status (required), note.

pathrule_setupPathrule SetupA
Read-only

Fetch the active Pathrule bootstrap brief and execute it. Call this ONCE when the user asks to set up / bootstrap / initialize Pathrule for a project (e.g. 'Set up Pathrule for this project', 'Bootstrap Pathrule'). The response body is a prompt you must follow immediately — it tells you how to scan the project, propose memories/rules/skills, and write the approved items via pathrule_write_memory / _rule / _skill. Do NOT call this mid-task, for already-populated workspaces, or when the user just wants context — use pathrule_get_context for routine context lookups. If no workspace exists yet, call pathrule_list_organizations + pathrule_create_workspace first.

Inputs: workspace_id, locale.

pathrule_take_snapshotPathrule Project SnapshotA

Record a point-in-time inventory of the user's project under a workspace. Remote MCP cannot see the filesystem, so YOU (the AI) collect this inventory with your own Read/Glob/Grep tools before calling this. Persist it so future setup, bootstrap, drift detection, and onboarding flows have structured evidence to reason over. Required: workspace_id. Strongly recommended: project_name, file_count, file_tree (cap at ~5000 entries — summarise deeper paths), file_extensions_summary, top_level_dirs, sampled_contents for README, package.json / pyproject.toml / Cargo.toml, CLAUDE.md, AGENTS.md, main config files (truncate each to ~4KB). Optional: git_head / branch / git_log_summary if you can read them, ai_notes for free-form observations.

Inputs: workspace_id (required), source, project_name, root_path, +12 more.

pathrule_update_memoryPathrule Update MemoryA
Destructive

Update a memory's content or title, optionally moving it. Uses optimistic concurrency via expected_version_id. Cloud-only.

Inputs: workspace_id (required), memory_id (required), content (required), title, +4 more.

pathrule_update_rulePathrule Update RuleB
Destructive

Update a rule's fields and/or path. Optimistic concurrency via expected_version_id. Cloud-only.

Inputs: workspace_id (required), rule_id (required), patch (required), expected_version_id, +2 more.

pathrule_update_skillPathrule Update SkillA
Destructive

Partially update an existing Pathrule skill record. Use pathrule_update_skill only when you already have a skill_id and want to change metadata, SKILL.md content, source/github_url, tags, or move the skill to another workspace path; use pathrule_write_skill to create a new skill, pathrule_read_skill to inspect the current body first, and pathrule_delete_skill to remove one. Requires an authenticated connector token with pathrule:write and an active workspace subscription. Side effects: writes the cloud skill record, may replace fields present in patch, may move the skill when move_to_path is set, and may fail on version conflict; it never installs files into .codex/skills, .claude/skills, or editor folders.

Inputs: workspace_id (required), skill_id (required), patch (required), expected_version_id, +1 more.

pathrule_write_memoryPathrule Write MemoryA

Create a new memory at a workspace path. Missing nodes auto-create. Blocks duplicate titles unless allow_duplicate is set. Cloud-only: never writes to the user's local filesystem. For automatic CLAUDE.md/AGENTS.md sync and on-disk hook injection alongside the write, install Pathrule Desktop or CLI.

Inputs: workspace_id (required), node_path (required), title (required), content (required), +3 more.

pathrule_write_rulePathrule Write RuleA

Create a new rule at a workspace path. Missing nodes auto-create. Use scope_type/priority honestly: high only when a violation causes a real bug or regression. Cloud-only — Pathrule Desktop/CLI also renders the rule into the user's CLAUDE.md/AGENTS.md and editor companion files automatically.

Inputs: workspace_id (required), node_path (required), name (required), content (required), +3 more.

pathrule_write_skillPathrule Write SkillA

Create a new skill at a workspace path. Content is the full SKILL.md body (frontmatter + markdown). For github_ref skills set source='github_ref' and github_url. Cloud-only: does NOT materialize the skill into .codex/skills, .claude/skills, .cursor/skills, etc. — Pathrule Desktop or CLI is required for on-disk skill materialization.

Inputs: workspace_id (required), node_path (required), name (required), description (required), +4 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 30 tools

    Disambiguation5/5

    Each tool targets a distinct action on a specific resource (workspace, memory, rule, skill, snapshot, etc.). Despite 30 tools, there is no functional overlap; descriptions clearly differentiate purposes.

    Naming Consistency5/5

    All tools follow a consistent `pathrule_verb_noun` snake_case pattern (e.g., pathrule_create_workspace, pathrule_delete_memory). No deviations in style or casing.

    Tool Count3/5

    30 tools is high, but the domain covers multiple entity types (workspaces, organizations, memories, rules, skills, snapshots, refresh tasks) plus workflow tools, justifying the count. It borders on heavy but is not excessive.

    Completeness4/5

    Covers CRUD for memories, rules, skills, and snapshots, plus workspace creation, navigation, context retrieval, and refresh workflows. Minor gaps: no workspace update/delete, no global list of rules/skills independent of a node.

    Maintenance

    ActivityNo data
    ResponsivenessSyncing

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Persistent shared memory for AI coding agents. Stores facts as entity/key/value triples with hybrid semantic search, task checkpoints, and conflict resolution — shared across Claude Code, Codex CLI, and GitHub Copilot.
      16
      235 npm
      5
      AGPL 3.0
    • F
      license
      A
      quality
      C
      maintenance
      Semantic memory for AI builders: capture the tacit engineering know-how that never reaches your docs, recall it the moment it applies. Built in Rust on Postgres and pgvector.
      10
      10
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Shared team memory for AI coding agents with Bayesian confidence scoring and temporal decay, enabling persistent storage and retrieval of engineering patterns across sessions.
      20 npm
      18
      MIT