// SCAN REPORT

Skillsmp

17 tools. 7 can modify or destroy data without limits.

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

Last updated: 5 Jul 2026

7 can modify or destroy data

10 read-only

17 tools total

Community server · catalogue entry verified 05/07/2026

How to control Skillsmp ↓

TOOL MAP

What Skillsmp exposes to your agents

Read (10) Write / Execute (7) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Skillsmp tools

Execute · Medium skillsmp_auto_discover This tool goes beyond passive reading: it analyzes conversation context and can automatically load skills without explicit user action for each one. Write · Low skillsmp_add_context The tool adds (creates/appends) a message to a discovery context, which is a reversible data modification operation. Write · Medium skillsmp_install Installing a skill writes new data or configurations to a namespace (global, project, or sandbox). Write · Medium skillsmp_promote This tool modifies the state/tier of a skill object reversibly—it changes a skill's tier classification from one level to a higher one.

7 of Skillsmp's 17 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Skillsmp

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

Rate limit write operations

{
  "skillsmp_add_context": {
    "limits": [
      {
        "counter": "skillsmp_add_context_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "skillsmp_ai_search": {
    "limits": [
      {
        "counter": "skillsmp_ai_search_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 Skillsmp — 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 SKILLSMP →

Instant setup, no code required.

FULL CATALOGUE

All 17 Skillsmp tools

EXECUTE 1 tools

Execute skillsmp_auto_discover Automatically discover and recommend skills based on conversation analysis. Analyzes context, searches for rel

WRITE 6 tools

Write skillsmp_add_context Add a message to the discovery context for analysis Write skillsmp_demote Manually demote a skill to a lower tier (hot→warm→sandbox) Write skillsmp_install Install a skill to specified namespace (global/project/sandbox) Write skillsmp_promote Manually promote a skill to a higher tier (sandbox→warm→hot) Write skillsmp_rate Rate a skill after using it (helpful/not-helpful/harmful). This feedback is used for intelligent tiering. Write skillsmp_unload Unload skill from active context

READ 10 tools

Read skillsmp_ai_search AI-powered semantic search with context awareness Read skillsmp_discover AI-powered skill discovery based on conversation context Read skillsmp_evaluate Evaluate all skills and automatically adjust tiers based on metrics Read skillsmp_list List installed skills with optional filters Read skillsmp_load Load skill content into active context Read skillsmp_metrics View detailed metrics and statistics for a skill, including relevance, success rate, and tier evaluation Read skillsmp_preview Preview skill metadata and content before installing Read skillsmp_search Search skills by keywords, category, or tags Read skillsmp_stats View usage statistics for skills Read skillsmp_vet Security scan skill content for potential risks

FAQ

Questions about Skillsmp

How do I prevent bulk modifications through Skillsmp? +

The Skillsmp server has 6 write tools including skillsmp_add_context, skillsmp_demote, skillsmp_install. 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 Skillsmp.

How many tools does the Skillsmp MCP server expose? +

17 tools across 2 categories: Read, Write. 10 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Skillsmp? +

Register the Skillsmp 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 Skillsmp tool call.

Deterministic rules across all 17 Skillsmp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SKILLSMP →

Instant setup, no code required.

17 Skillsmp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.