ToolRoute

Route every task to the best MCP server and cheapest LLM. Scores on real execution data across quality, reliability, speed, cost, and trust.

Security Scan

The skill's instructions are broadly coherent with a routing service (it sends task descriptions to an external API), but metadata/instruction mismatches, an unknown publisher/homepage, and the fact that user task text is sent off-device (possible sensitive data leakage) make this worth caution before installing.

Purpose & Capability

The SKILL.md behavior (POST task descriptions to https://toolroute.io to obtain an MCP server/model and optionally report outcome) aligns with the declared purpose of routing tasks to the best server/model. However, the registry metadata claims no required binaries or env vars while the SKILL.md lists curl as a required binary and instructs storing TOOLROUTE_AGENT_ID in an environment variable — an inconsistency that should be resolved by the publisher.

Instruction Scope

Instructions explicitly send natural-language task descriptions and telemetry to an external service. While the doc warns to generalize sensitive details, the skill depends on sending user-provided task text off-host, which can leak secrets if users are careless. The instructions do not request reading local files or other system credentials, which is good, but the allowed data flow to an external endpoint is the main risk.

Install Mechanism

This is an instruction-only skill with no install spec or code files, reducing on-disk risk. It mentions optional npm SDKs (@toolroute/sdk, @toolroute/hook) but does not require them. No downloads or extraction steps are present.

Credentials

Registry metadata lists no required env vars, yet SKILL.md asks users to store a returned agent_identity_id in an environment variable (TOOLROUTE_AGENT_ID). That single env var is plausible for attribution/credits, but the mismatch between metadata and instructions is confusing. The skill does not ask for unrelated secrets (AWS keys, tokens) which is proportional, but the agent ID could still be sensitive and link agent activity to your account.

Persistence & Privilege

The skill does not request always: true and is user-invocable only; autonomous invocation is allowed by default (normal). It does not claim to modify other skills or system-wide configs. No elevated persistence privileges are requested.

What to consider before installing

This skill routes task descriptions to an external service (toolroute.io). Before installing: 1) Confirm the publisher and privacy policy (metadata shows no homepage/source but SKILL.md links to toolroute.io). 2) Do not send raw sensitive text — generalize or redact names, secrets, PII. 3) If you register, treat the returned agent_identity_id as a credential (store it securely and avoid committing it). 4) Prefer using the skill only for non-sensitive tasks until you verify the service (check TLS cert, privacy policy, and reputational signals). 5) Ask the publisher to fix metadata mismatches (declared required binaries/env) so the skill description accurately reflects runtime requirements.

ToolRoute - Intelligent Task Routing

Before every task, ask ToolRoute which MCP server and LLM model to use. It recommends based on real execution data scored across 5 dimensions.

Privacy and Data Handling

What is sent: A natural language task description (e.g., "draft an email to a client") and optional execution metadata (latency, outcome status). No file contents, credentials, API keys, or personal data are sent.

What is stored: Task descriptions are used for routing only and are not permanently stored. Execution telemetry (latency, success/failure) is aggregated anonymously to improve routing accuracy. See https://toolroute.io/privacy for the full policy.

Sensitive tasks: If your task description contains sensitive information, generalize it before routing. Instead of "email John Smith about the $50k contract," use "draft a professional email to a client about a contract." The routing engine only needs the task type, not the details.

Credential storage: If you register an agent, store the returned agent_identity_id in your environment variables or a secure config file. Do not hardcode it in shared scripts.

What this skill does

When activated, this skill:

1. Routes your current task through https://toolroute.io/api/route
2. Returns the best MCP server, model, and fallback chain
3. After execution, optionally reports the outcome to improve future routing

Quick start

Route a task:

curl -s -X POST https://toolroute.io/api/route \
  -H "Content-Type: application/json" \
  -d '{"task": "YOUR_TASK_DESCRIPTION"}'

Report the outcome (optional, earns routing credits):

curl -s -X POST https://toolroute.io/api/report \
  -H "Content-Type: application/json" \
  -d '{"skill_slug": "SKILL_USED", "outcome_status": "success", "latency_ms": 1200}'

Registration (optional, earns 2x credits)

curl -s -X POST https://toolroute.io/api/agents/register \
  -H "Content-Type: application/json" \
  -d '{"agent_name": "YOUR_AGENT_NAME"}'

Store the returned agent_identity_id in an environment variable:

export TOOLROUTE_AGENT_ID="your-returned-id"

Include it in future route/report calls for credit tracking.

Model routing

Get the best model for your task at the lowest cost:

curl -s -X POST https://toolroute.io/api/route/model \
  -H "Content-Type: application/json" \
  -d '{"task": "YOUR_TASK_DESCRIPTION"}'

Verification (earns permanent 2x credits)

1. Call POST /api/verify/initiate with your agent name
2. Send the returned claim URL to your human owner
3. They tweet and verify - you earn 2x credits forever

Integration pattern

Before every task:

1. Describe your task in natural language (generalize sensitive details)
2. POST to /api/route - get recommended skill + model
3. Execute using the recommended tool
4. POST to /api/report - earn credits, improve routing (optional)

Links

• Catalog: https://toolroute.io/servers
• Models: https://toolroute.io/models
• Challenges: https://toolroute.io/challenges (earn 3x credits)
• API docs: https://toolroute.io/api-docs
• Privacy policy: https://toolroute.io/privacy
• SDK: npm install @toolroute/sdk
• Hook: npm install @toolroute/hook