Planning Game

48 tools. 27 can modify or destroy data without limits.

5 destructive tools with no built-in limits. Policy required.

Last updated:

27 can modify or destroy data
21 read-only
48 tools total

Community server · catalogue entry verified 30/06/2026

How to control Planning Game ↓

What Planning Game exposes to your agents

Read (21) Write / Execute (22) Destructive / Financial (5)
Critical Risk

The most dangerous Planning Game tools

27 of Planning Game's 48 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Planning Game

PolicyLayer is an MCP gateway — it sits between your AI agents and Planning Game, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "delete_adr": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "create_adr": {
    "limits": [
      {
        "counter": "create_adr_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "discover_project": {
    "limits": [
      {
        "counter": "discover_project_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Planning Game — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON PLANNING GAME →

Instant setup, no code required.

All 48 Planning Game tools

WRITE 20 tools
Write create_adr Create a new ADR (Architecture Decision Record) Write create_card create_card Write create_global_config Create a new global config (agent, prompt, instruction, or guideline). Guidelines require content and support Write create_plan Create a new development plan with phases and proposed tasks Write create_plan_proposal Create a new plan proposal (feature request that can later generate technical plans) Write create_project Create a new project. REQUIRED: name, abbreviation (3-4 uppercase letters). Optional: description, repoUrl, la Write create_sprint Create a new sprint. REQUIRED: projectId, title, startDate (YYYY-MM-DD), endDate (YYYY-MM-DD). Optional: devPo Write provision_user Provision a new user or update an existing one in /users/. Creates user record, auto-generates developer/stake Write publish_mcp_version Publish MCP version to Firebase so other users get update notifications. Call after pushing changes. Write relate_cards Create or remove relations between cards. REQUIRED: projectId, sourceCardId, targetCardId, relationType ( Write restore_guideline_version Restore a guideline to a previous version. Creates a new version with the content from the specified historica Write setup_mcp_user Configure MCP user identity. Accepts name, email, or developerId to auto-match. Without params: lists develope Write sync_guidelines Download guidelines from Firebase and write them as local files. Compares versions to only update changed guid Write update_adr Update an existing ADR Write update_card update_card Write update_global_config Update an existing global config. For guidelines: auto-increments version and saves previous content in histor Write update_plan Update a development plan (title, objective, status, phases) Write update_plan_proposal Update a plan proposal (title, description, status, tags, planIds) Write update_project Update fields of an existing project (description, repoUrl, languages, frameworks, agentsGuidelines, etc.) Write update_sprint Update fields of an existing sprint
READ 21 tools
Read discover_project Discover a project by its repository URL (supports HTTPS, SSH, with/without .git) Read get_adr Get full details of an ADR Read get_card Get full details of a card by its cardId Read get_global_config Get full details of a global config Read get_guideline_history Get version history of a guideline including current version and all previous versions with timestamps Read get_mcp_status Get MCP server status including version and update availability Read get_plan Get full details of a development plan including phases and proposed tasks Read get_plan_proposal Get full details of a plan proposal including linked plan IDs Read get_project Get full details of a project including description, repos, languages, frameworks, and team Read get_sprint Get full details of a sprint by its cardId Read get_transition_rules Get status transition rules for cards. Call this BEFORE attempting status updates to understand requirements. Read list_adrs List all ADRs for a project Read list_cards List cards of a project filtered by type, status, sprint, developer, or year Read list_developers List all developers (dev_XXX IDs). Call this BEFORE assigning developers to cards. Optional: projectId to filt Read list_global_config List all global configs of a type (agents, prompts, instructions, guidelines) Read list_plan_proposals List plan proposals for a project, optionally filtered by status (pending, planned, rejected) Read list_plans List development plans for a project, optionally filtered by status (draft, accepted, rejected) Read list_projects List all projects with name, abbreviation, and developers Read list_sprints List sprints of a project with dates and points Read list_stakeholders List all stakeholders (stk_XXX IDs). Call this BEFORE creating tasks — validator is REQUIRED and must be a val Read pg_config View MCP server configuration: instance name, Firebase project, credentials path, user config, environment var

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Planning Game

Can an AI agent delete data through the Planning Game MCP server? +

Yes. The Planning Game server exposes 5 destructive tools including delete_adr, delete_global_config, delete_plan. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Planning Game? +

The Planning Game server has 20 write tools including create_adr, create_card, create_global_config. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Planning Game.

How many tools does the Planning Game MCP server expose? +

48 tools across 4 categories: Destructive, Execute, Read, Write. 21 are read-only. 27 can modify, create, or delete data.

How do I enforce a policy on Planning Game? +

Register the Planning Game MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Planning Game tool call.

Deterministic rules across all 48 Planning Game tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

48 Planning Game tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.