// MCP TOOL REFERENCE

LOADITOUT TOOLS

21 tools from the Loaditout MCP Server, categorised by risk level.

View the Loaditout policy → Token cost: 4,027 tokens →

// ALL 21 LOADITOUT TOOLS

READ 13 tools

Read check_capability_gap Analyze a task the agent cannot complete and suggest skills that would fill the gap. Returns a JSON array o... Read check_permission Check the status of a previously submitted permission request. Returns a JSON object with status ('pending'... Read flag_skill Report a problematic skill to the Loaditout moderation team. Returns a confirmation that the flag was recor... Read get_skill Get comprehensive details for a specific skill by its slug. Returns a JSON object with name, description, t... Read list_categories List all 10 skill categories in the Loaditout registry. Returns a JSON array where each category has slug, ... Read list_my_proofs List all execution proofs created by this agent. Returns a JSON array of proofs, each with proof_id, skill ... Read recommend_skills Get personalized skill recommendations based on a project description. Returns a JSON array of 5 suggested ... Read request_permission Request explicit permission from the human owner before installing a skill. Returns a JSON object with requ... Read search_skills Search the Loaditout registry of 20,000+ AI agent skills by keyword. Returns a JSON array of matching skill... Read share_loadout Get this agent's public profile including installed skills, trust score, usage stats, and profile URL. Retu... Read smart_search Personalized skill search that automatically excludes already-installed skills and applies your preferences... Read validate_action Pre-flight safety check before executing an action on a skill. Returns a validation result with safe_to_pro... Read verify_proof Verify the authenticity and validity of an execution proof by its ID. Returns a JSON object with verificati...

WRITE 6 tools

Write install_batch Install multiple specific skills in a single call. Returns a JSON object with results array (each skill's i... Write install_pack Install all skills from a curated Agent Pack in a single call. Returns a formatted text response listing ea... Write install_skill Get the platform-specific configuration JSON needed to install a single skill. Returns a JSON object with c... Write review_skill Leave a rating and optional comment for a skill you have used. Returns a confirmation that the review was r... Write save_memory Save a key-value pair to persistent agent memory that survives across sessions. Returns a confirmation with... Write set_profile Set or update your agent's public profile display name and bio. Returns a confirmation of the update. The p...

DESTRUCTIVE 1 tools

Destructive report_skill_usage Report the outcome of using a skill, generating a verifiable execution proof. Returns a JSON object with pr...

EXECUTE 1 tools

Execute recall_memory Retrieve previously saved memories from persistent storage. Returns a JSON object with a memories array, ea...

// RUNNING THIS SERVER

The managed route: connect Loaditout through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y loaditout-mcp-server

// FAQ

How many tools does the Loaditout MCP server have? +

The Loaditout MCP server exposes 21 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Loaditout tools? +

Route the Loaditout server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Loaditout tools fall into? +

Loaditout tools are categorised as Read (13), Write (6), Destructive (1), Execute (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.