// SCAN REPORT

Planning System MCP Server

37 tools. 28 can modify or destroy data without limits.

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

Last updated: 29 Jun 2026

28 can modify or destroy data

9 read-only

37 tools total

Community server · catalogue entry verified 29/06/2026

How to control Planning System MCP Server ↓

TOOL MAP

What Planning System MCP Server exposes to your agents

Read (9) Write / Execute (25) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Planning System MCP Server tools

Destructive · High delete_blueprint Delete a blueprint you own. Hard delete (the snapshot is removed); plans Destructive · High remove_member Remove a member from an organization. Caller must be org owner or Destructive · High unlink_intentions Remove a dependency edge by id. Write · Medium add_learning Record a knowledge episode. Use after research, on decisions, or when discovering

28 of Planning System MCP Server's 37 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Planning System MCP Server

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

Deny destructive operations

{
  "delete_blueprint": {
    "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

{
  "add_learning": {
    "limits": [
      {
        "counter": "add_learning_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_started": {
    "limits": [
      {
        "counter": "get_started_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

Create a free account and register Planning System MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON PLANNING SYSTEM →

Instant setup, no code required.

FULL CATALOGUE

All 37 Planning System MCP Server tools

DESTRUCTIVE 3 tools

Destructive delete_blueprint Delete a blueprint you own. Hard delete (the snapshot is removed); plans Destructive remove_member Remove a member from an organization. Caller must be org owner or Destructive unlink_intentions Remove a dependency edge by id.

WRITE 25 tools

Write add_learning Record a knowledge episode. Use after research, on decisions, or when discovering Write briefing Mission control state in one call. Returns goal health summary, Write claim_next_task Pick the next task in scope, claim it, and return its context — all in Write create_goal Create a new top-level goal (no parent). Use this when a human asks you to Write create_workspace Create a new workspace inside an organization. Returns the new workspace Write derive_subgoal Create a sub-goal under an existing parent goal (parent_goal_id required). Write extend_intention Add children under an existing phase or task. Use when an agent has Write fork_blueprint Fork a plan-scope blueprint into a target workspace. Creates a new plan Write form_intention Create a plan that achieves a goal, including an initial phase/task Write invite_member Add a user to an organization by user_id or email. Caller must be Write link_intentions Create a dependency edge between two existing tasks. Use to express Write move_node Reparent a node within the same plan. Cycle-safe (server rejects Write plan_analysis Advanced plan reads: impact analysis (delay/block/remove), critical path, Write propose_research_chain Create a Research → Plan → Implement triple under an existing parent Write queue_decision Queue a decision for human review. Writes to the real decisions table Write record_criterion_progress Record the latest observed value of one of a goal Write release_task Release a claimed task without changing status. Use for explicit handoff or abandonment. Write resolve_decision Resolve a pending decision. action is Write save_as_blueprint Snapshot a live plan as a new plan-scope blueprint. Captures structure, Write share_plan Atomically change a plan Write update_goal Atomic goal update. Subsumes update_goal + link_plan_to_goal + unlink_plan_from_goal Write update_member_role Change a member Write update_node Edit any node property atomically: title, description, node_type, Write update_plan Edit any plan property atomically: title, description, status, Write update_task Atomic task state transition. Updates status, optionally appends a log

READ 9 tools

Read get_started Call this FIRST when you are new to AgentPlanner or unsure which tool to use Read goal_state Comprehensive single-goal read: details, quality assessment, progress, Read list_blueprints List blueprints visible to the user (owned + public/unlisted). Filter by Read list_goals List goals with health rollup. Returns aggregate counts (on_track/at_risk/stale) Read list_plans List plans with optional filters by status, visibility, or text query. Read list_workspaces List workspaces in an organization. A workspace is a folder that owns Read recall_knowledge Universal knowledge graph query. Returns facts, entities, recent episodes, Read search Text search across plans, nodes, and content. Use for finding entities by title or fragment. Read task_context Get progressive context for a task. Depth: 1 (task only), 2 (+ neighborhood),

EXPLORE

Related servers

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

FAQ

Questions about Planning System MCP Server

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

Yes. The Planning System MCP Server server exposes 3 destructive tools including delete_blueprint, remove_member, unlink_intentions. 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 System MCP Server? +

The Planning System MCP Server server has 25 write tools including add_learning, briefing, claim_next_task. 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 System MCP Server.

How many tools does the Planning System MCP Server MCP server expose? +

37 tools across 3 categories: Destructive, Read, Write. 9 are read-only. 28 can modify, create, or delete data.

How do I enforce a policy on Planning System MCP Server? +

Register the Planning System MCP Server 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 System MCP Server tool call.

Deterministic rules across all 37 Planning System MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PLANNING SYSTEM →

Instant setup, no code required.

37 Planning System MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.