Skip to main content
Glama

Safest MCP server for a task (7Maps)

route
Read-onlyIdempotent

Use this when you need a tool for a task and do not know which MCP server to use, or when several could do it: finds servers whose tools match the task and ranks them by the chance the call works, how stable the server is, and least privilege (a server that can do less harm than another is preferred when both can do the task). Returns the best server and tool, alternatives and servers to avoid. Placement is never sold: the order comes only from live checks and real use. Which to use: route picks for you; find_tool lets you search tools yourself; resolve returns a signed list a client can verify. Paid per task (see list_paid_tools). Reads the map only.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task": "<task>"
    },
    "name": "route"
  }
}

Input Schema

NameRequiredDescriptionDefault
needNoHow much the task must be allowed to do: read only, change something, or a high-risk action such as payments or deletion. Guessed from the task when omitted
taskYesWhat you need to do, for example "send a transactional email" or "search company records"
paymentNoPayment terms: any (default); free_only = only servers that declare no payment; paid_ok = servers that charge are fine, servers whose payment terms are unknown are left out. Paid servers show their declared price per call.
last_tripNoOptional: how your previous call to a server 7Maps named went
task_typeNoOptional: kind of work (only the category is kept)
agent_modelNoOptional: your model id, e.g. "claude-sonnet-5-5". Anonymous
license_keyNo7IT plan license key; else pay per call (x402)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed14 schema fields changed
    • changedInput schema / properties / agent_model / description
      Previous value: -"Optional: the model you run on, for example \"claude-sonnet-5-5\", \"gpt-5\", \"llama3.2:3b\". Anonymous; it helps 7Maps learn which servers work for which models"New value: +"Optional: your model id, e.g. \"claude-sonnet-5-5\". Anonymous"
    • changedInput schema / properties / last_trip / description
      Previous value: -"Optional: how your previous call to an MCP server went (one 7Maps named), as the last 7Maps answer shows."New value: +"Optional: how your previous call to a server 7Maps named went"
    • changedInput schema / properties / last_trip / properties / charged_usd / description
      Previous value: -"What the server charged, if anything"New value: +"Charged in USD"
    • changedInput schema / properties / last_trip / properties / fail / description
      Previous value: -"If it failed: unreachable, auth, args, server_error, timeout, rate_limited or wrong_result"New value: +"Why it failed"
    • changedInput schema / properties / last_trip / properties / matched_description / description
      Previous value: -"Whether the result matched what the tool description promised"New value: +"Result matched the tool description"
    • changedInput schema / properties / last_trip / properties / ms / description
      Previous value: -"How long the call took, in milliseconds"New value: +"Duration in ms"
    • changedInput schema / properties / last_trip / properties / ok / description
      Previous value: -"Whether the call did what you needed"New value: +"Did it do what you needed"
    • changedInput schema / properties / last_trip / properties / result_tokens / description
      Previous value: -"About how many tokens the result was"New value: +"Result size in tokens"
    • changedInput schema / properties / last_trip / properties / server / description
      Previous value: -"The MCP server you called (URL or registry name)"New value: +"Server called (URL or registry name)"
    • changedInput schema / properties / last_trip / properties / surprise / description
      Previous value: -"Anything the tool did that you did not ask for"New value: +"Side effect you did not ask for"
    • changedInput schema / properties / last_trip / properties / tool / description
      Previous value: -"The tool you called"New value: +"Tool called"
    • changedInput schema / properties / last_trip / properties / tools_hash / description
      Previous value: -"The tool_list_hash of the tool list you received, if you computed it as 7Maps does"New value: +"tool_list_hash, computed as 7Maps does"
    • changedInput schema / properties / license_key / description
      Previous value: -"A 7IT monthly plan license key, if you have one; otherwise pay per call with x402"New value: +"7IT plan license key; else pay per call (x402)"
    • changedInput schema / properties / task_type / description
      Previous value: -"Optional: the kind of work you are doing right now. Only this category is kept, never your task text"New value: +"Optional: kind of work (only the category is kept)"
  2. Changed1 schema field changed
    • changedInput schema / properties / last_trip / description
      Previous value: -"Optional: how your last call to an MCP server went (the one 7Maps pointed you to). It keeps the map honest; accepted reports from a paying wallet earn calls at no charge."New value: +"Optional: how your previous call to an MCP server went (one 7Maps named), as the last 7Maps answer shows."
  3. Changed2 schema fields changed
    • addedInput schema / properties / agent_model
      Added value: +{
      +  "description": "Optional: the model you run on, for example \"claude-sonnet-5-5\", \"gpt-5\", \"llama3.2:3b\". Anonymous; it helps 7Maps learn which servers work for which models",
      +  "maxLength": 80,
      +  "type": "string"
      +}
    • addedInput schema / properties / task_type
      Added value: +{
      +  "description": "Optional: the kind of work you are doing right now. Only this category is kept, never your task text",
      +  "enum": [
      +    "coding",
      +    "research",
      +    "data",
      +    "communication",
      +    "commerce",
      +    "devops",
      +    "content",
      +    "personal_assistant",
      +    "testing",
      +    "other"
      +  ],
      +  "type": "string"
      +}
  4. Changed1 schema field changed
    • addedInput schema / properties / payment
      Added value: +{
      +  "description": "Payment terms: any (default); free_only = only servers that declare no payment; paid_ok = servers that charge are fine, servers whose payment terms are unknown are left out. Paid servers show their declared price per call.",
      +  "enum": [
      +    "any",
      +    "free_only",
      +    "paid_ok"
      +  ],
      +  "type": "string"
      +}
  5. Changed1 schema field changed
    • changedInput schema / properties / last_trip / description
      Previous value: -"Optional: how your last call to an MCP server went (the one 7Maps pointed you to). It keeps the map honest; 5 accepted reports from a paying wallet earn 1 call at no charge."New value: +"Optional: how your last call to an MCP server went (the one 7Maps pointed you to). It keeps the map honest; accepted reports from a paying wallet earn calls at no charge."
  6. Changed1 schema field changed
    • changedInput schema / properties / last_trip / description
      Previous value: -"Optional: how your last call to an MCP server went (the one 7Maps pointed you to). It keeps the map honest; 5 accepted reports from a paying wallet earn 1 free call."New value: +"Optional: how your last call to an MCP server went (the one 7Maps pointed you to). It keeps the map honest; 5 accepted reports from a paying wallet earn 1 call at no charge."
  7. First observed

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so 'Reads the map only' largely restates them. The description does add genuinely new behavior: the ranking criteria and their ordering, the fact that placement is not sold, the billing model ('Paid per task (see list_paid_tools)'), and that low-privilege servers are preferred when several qualify. It does not mention rate limits or how stale rankings can be.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The when-to-use condition is front-loaded, and the sentence separating route from find_tool and resolve is tightly packed and useful. A couple of clauses, notably the anti-promotional 'Placement is never sold' line and the redundant 'Reads the map only', could be trimmed without losing callable information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully summarizes what comes back (best server and tool, alternatives, servers to avoid), which is the main thing an agent needs. Against a 7-parameter tool with a nested object, the notable gap is that the description never mentions the optional last_trip feedback that presumably sharpens future rankings, so an agent may skip a parameter the tool clearly values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and each of the 7 parameters, including the nested last_trip object and its enums, is documented in-schema. The description adds no parameter-level meaning beyond a passing reference to payment terms and the pointer to list_paid_tools. In particular, the feedback loop value of last_trip is left entirely to the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb+resource ('finds servers whose tools match the task and ranks them') and states the ranking criteria (success chance, stability, least privilege) plus the return shape (best server and tool, alternatives, servers to avoid). It also distinguishes itself from siblings by role: 'route picks for you; find_tool lets you search tools yourself; resolve returns a signed list a client can verify.'

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It opens with the exact triggering condition ('when you need a tool for a task and do not know which MCP server to use, or when several could do it') and then names three siblings with the condition that selects each. An agent does not need to infer when to prefer route over find_tool or resolve.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources