mcpcost

Look up a registry server on the board

lookup_server

Read-onlyIdempotent

Look up a registered MCP server's daily probe—status, access, Claude token cost, tool count, latency, and change history—by registry name or endpoint URL, without contacting the server.

Instructions

Reads the public board's latest daily probe of one server in the official MCP registry: status, how a client gets access, the exact Claude token cost of its tool definitions, tool count, latency and the history of changes. Instant, no connection to the server, with a registry name or with the endpoint URL as the registry lists it. Use it when the server is in the registry; use search_servers when you do not know its name, and measure_server to probe a URL or a local command here and now. A name or URL that is not on the board returns isError with a short message that points to measure_server.

Input Schema

Name	Required	Description	Default
`nameOrUrl`	Yes	The registry name, for example io.github.owner/name, or the https URL of the endpoint as the registry lists it; both are looked up on the board, nothing is contacted

Output Schema

Name	Required	Description
`url`	No	The endpoint the board probes
`name`	No	The registry name
`page`	No	The server's page on the board
`title`	No
`status`	No	ok (answered initialize and tools/list), auth (needs credentials), payment (402), not_found, protocol_error (not MCP), timeout, dns, tls, refused, server_error, rate_limited, newer_protocol, or for a local command: install_failed, no_bin, needs_env, needs_args, needs_network, crashed
`authKind`	No	How a client gets in: oauth-dcr (clients register themselves), oauth (client id from the publisher), token (a key in the Authorization header), unknown
`probedAt`	No	ISO 8601 time of the probe
`topTools`	No	The five most expensive tools: name and o200k_base tokens
`latencyMs`	No	initialize and toolsList, milliseconds
`toolCount`	No	How many tools tools/list returned
`authScheme`	No	The WWW-Authenticate scheme of a server that needs auth
`httpStatus`	No
`claudeModel`	No	The model the exact count is for
`shareOf200k`	No	Percent of a 200k window, exact when claudeTokens is present
`statusLabel`	No	The status in words, as the board shows it
`toolsTokens`	No	o200k_base estimate over the compact JSON of the tool definitions
`claudeTokens`	No	Exact count from the Anthropic count_tokens endpoint, names as published
`protocolVersion`	No	The MCP protocol version the server negotiated
`authDocumentation`	No	The publisher's guide to getting access
`claudeTokensClaudeCode`	No	The same with the Claude Code prefix mcp__<server>__ on each tool name

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 24, 2026

changedInput schema / properties / nameOrUrl / description

Previous value: -"The registry name, for example io.github.owner/name (exact, instant), or an https URL of an MCP endpoint (probed live by the board)"New value: +"The registry name, for example io.github.owner/name, or the https URL of the endpoint as the registry lists it; both are looked up on the board, nothing is contacted"

Changed2 schema fields changedv0.3.4Oct 24, 2026

addedInput schema / properties / nameOrUrl / description

Added value: +"The registry name, for example io.github.owner/name (exact, instant), or an https URL of an MCP endpoint (probed live by the board)"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "authDocumentation": {
+      "description": "The publisher's guide to getting access",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "authKind": {
+      "description": "How a client gets in: oauth-dcr (clients register themselves), oauth (client id from the publisher), token (a key in the Authorization header), unknown",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "authScheme": {
+      "description": "The WWW-Authenticate scheme of a server that needs auth",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "claudeModel": {
+      "description": "The model the exact count is for",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "claudeTokens": {
+      "description": "Exact count from the Anthropic count_tokens endpoint, names as published",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "claudeTokensClaudeCode": {
+      "description": "The same with the Claude Code prefix mcp__<server>__ on each tool name",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "httpStatus": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "latencyMs": {
+      "description": "initialize and toolsList, milliseconds",
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "name": {
+      "description": "The registry name",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "page": {
+      "description": "The server's page on the board",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "probedAt": {
+      "description": "ISO 8601 time of the probe",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "protocolVersion": {
+      "description": "The MCP protocol version the server negotiated",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "shareOf200k": {
+      "description": "Percent of a 200k window, exact when claudeTokens is present",
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "status": {
+      "description": "ok (answered initialize and tools/list), auth (needs credentials), payment (402), not_found, protocol_error (not MCP), timeout, dns, tls, refused, server_error, rate_limited, newer_protocol, or for a local command: install_failed, no_bin, needs_env, needs_args, needs_network, crashed",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "statusLabel": {
+      "description": "The status in words, as the board shows it",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "title": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "toolCount": {
+      "description": "How many tools tools/list returned",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "toolsTokens": {
+      "description": "o200k_base estimate over the compact JSON of the tool definitions",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "topTools": {
+      "description": "The five most expensive tools: name and o200k_base tokens",
+      "type": [
+        "array",
+        "null"
+      ]
+    },
+    "url": {
+      "description": "The endpoint the board probes",
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "type": "object"
+}

First observedv0.1.0Oct 15, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds meaningful traits: the data is a cached daily probe, the call is instant, and nothing contacts the target server. It also discloses the failure behavior (isError with a short message). It stops short of saying how stale the board data can be or how history entries are shaped, which the output schema covers.

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?

Front-loads the resource and returned fields, then the usage routing, then the failure mode — a sensible order. Dense but each clause carries information; slightly overstuffed as a single run-on sequence.

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

Completeness5/5

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

For a one-parameter read tool with full annotations and an output schema, the description covers what it returns, when to prefer it, which siblings to use otherwise, and what happens on a miss. Nothing an agent needs to pick or invoke it correctly is missing.

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 coverage is 100% and the single parameter already documents both accepted forms (registry name like io.github.owner/name, or https endpoint URL). The description repeats the same facts ('with a registry name or with the endpoint URL as the registry lists it') without adding format constraints or edge cases, so 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?

States a specific verb ('reads') and resource ('the public board's latest daily probe of one server in the official MCP registry') and enumerates the returned fields. It explicitly distinguishes itself from siblings search_servers and measure_server, so an agent can route without opening any schema.

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?

Gives an explicit when-to-use rule ('when the server is in the registry') plus the two alternative paths: search_servers for unknown names, measure_server for live probing. It also documents the negative path — unknown name/URL returns isError pointing at measure_server.

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

Deploy Server