// SCAN REPORT

Spine

16 tools. 11 can modify or destroy data without limits.

11 write tools that can modify data. Rate limits recommended.

Last updated: 29 Sept 2026

11 can modify or destroy data

5 read-only

16 tools total

Community server · catalogue entry checked 29/09/2026

How to control Spine ↓

TOOL MAP

What Spine exposes to your agents

Read (5) Write / Execute (11) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Spine tools

Execute · Medium spine_clean The tool runs a CLI command (Spine CLI with -m flag) which constitutes executing an external process. Execute · High spine_build_animation_from_json This tool executes a multi-step automated pipeline (analyze, generate, import, pack, export, open) that triggers multiple external operations and file system modifications. Execute · Medium spine_open_project This tool launches an external GUI application (the Spine editor) to open a project file. Execute · Medium spine_learn_from_corpus Use this to build the local Spine Corpus Learning Layer. It scans .json and .spine projects, exports .spine files to .cache/corpus-json when

11 of Spine's 16 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Spine

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

Rate limit write operations

{
  "spine_add_simple_animation": {
    "limits": [
      {
        "counter": "spine_add_simple_animation_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "spine_analyze_json": {
    "limits": [
      {
        "counter": "spine_analyze_json_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 Spine — 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 SPINE →

Instant setup, no code required.

FULL CATALOGUE

All 16 Spine tools

EXECUTE 4 tools

Execute spine_build_animation_from_json One-step JSON animation pipeline: analyze source JSON, generate animated copy, import to .spine, optionally pa Execute spine_clean Use this to run Spine CLI animation clean up with -m on a project or supported input. Do not use it to delete Execute spine_learn_from_corpus Use this to build the local Spine Corpus Learning Layer. It scans .json and .spine projects, exports .spine fi Execute spine_open_project Use this to open a .spine project in the local Spine application so you can continue manual editing. Do not us

WRITE 7 tools

Write spine_add_simple_animation Low-level debug tool for adding one simple rotate, translate, or scale bone timeline to a Spine JSON copy. Use Write spine_build_animation_from_existing_project Build simple animation keyframes on an existing Spine JSON or .spine project. Writes to outputDir, imports int Write spine_control_bones Write custom rotate, translate, and scale timelines for one or more existing bones into a Spine JSON copy. Use Write spine_create_loading_animation_preset Create a loading animation preset on a Spine JSON copy. Presets: cute_cat_loading, logo_bounce, breathing_idle Write spine_export Use this to export a .spine project with the official Spine CLI and an export settings JSON file. Do not use i Write spine_generate_animation_json Generate a modified Spine JSON copy by adding basic animation keyframes to an existing skeleton. Supports brea Write spine_import_json Use this to import Spine JSON, binary skeleton data, or another supported input into a .spine project via the

READ 5 tools

Read spine_analyze_json Read-only Spine JSON inspection tool. Use this to list skeleton metadata, bones, slots, skins, attachments, an Read spine_get_generation_guide Use this to load the learned Spine generation guide and machine-readable presets before deciding animation par Read spine_info Use this to inspect Spine project, JSON, binary skeleton, or folder metadata through the Spine CLI. Do not use Read spine_recommend_animation_params Use this to turn a user goal into recommended BasicAnimationRequest parameters using learned corpus presets an Read spine_scan_corpus Use this read-only tool to confirm a corpus path before learning. It recursively scans for .spine and .json fi

EXPLORE

Related servers

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

FAQ

Questions about Spine

How do I prevent bulk modifications through Spine? +

The Spine server has 7 write tools including spine_add_simple_animation, spine_build_animation_from_existing_project, spine_control_bones. 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 Spine.

How many tools does the Spine MCP server expose? +

16 tools across 4 categories: Destructive, Execute, Read, Write. 5 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on Spine? +

Register the Spine 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 Spine tool call.

Deterministic rules across all 16 Spine tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SPINE →

Instant setup, no code required.

16 Spine tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Spine's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →