Skip to main content
Glama
Cambrian API MCP

Cambrian API MCP

Official

cambrian_docs

Fetches Cambrian API documentation for an endpoint path, tool name, or search query, returning request schemas, response fields, examples, and guides so you can call DeFi and social data endpoints correctly.

Instructions

Get Cambrian API documentation from docs.cambrian.org/llms.txt. Provide an endpoint or guide path (e.g. "solana/price-current", "evm/dexes", "evm/42161/dexes", "deep42/social-data/sentiment-shifts", "guides/x402"). Endpoint detail defaults to the request schema. Use detail="response" for response fields or detail="full" for examples and all endpoint prose. Every endpoint detail includes the OpenAPI request schema, so do not use full only to get request fields. Use "guides/" for any guide listed in the live root index. Use evm endpoint paths for Base, Ethereum mainnet, Arbitrum One, Robinhood Chain, and BNB Smart Chain tools. Use tool_name when you know the exact MCP endpoint tool. If the exact path and tool name are unknown, use query only. Send only one of path, tool_name, or query. Omit all three to get a concise directory of endpoint groups, endpoint paths, and guides.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "cambrian_docs"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoEndpoint path to fetch docs for. E.g. "solana/price-current", "evm/dexes", "deep42/social-data/sentiment-shifts". Prefix an EVM path with a chain to scope it: "evm/8453/dexes", "evm/1/dexes", or "evm/42161/dexes". Omit for the root llms.txt index.
queryNoSearch the root index for relevant endpoint paths. Provide query without path.
detailNoUse schema for request parameters. Response detail also includes the OpenAPI request schema. Use full only for examples and all endpoint prose.schema
tool_nameNoExact MCP endpoint tool name. Use this instead of path or query.
_maxResponseLengthNoOptional maximum response length in characters. Default: 30000.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.6.0

TDQS

A4.4/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does disclose output behavior well: each detail level's contents, the fact that request schema is always included, and the root-index fallback. It does not mention rate limits, authentication, or output format (markdown vs JSON), which leaves minor gaps for a no-annotation tool.

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?

Purpose is front-loaded in the first sentence and most subsequent sentences add a distinct rule. There is some redundancy, since the example paths ('solana/price-current', 'evm/dexes', etc.) are repeated verbatim in the schema descriptions, and the description is dense and run-on, but little is truly wasted.

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?

For a 5-parameter tool with no output schema, the description explains what each detail level returns and what the argument-free call produces, which is the information an agent needs to call it correctly. Minor gaps remain around output format and response-size behavior, and _maxResponseLength is only documented in the schema.

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

Parameters5/5

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

Schema coverage is 100%, but the description still adds real meaning beyond it: mutual exclusivity of path/tool_name/query, the default behavior when all are omitted, and the non-obvious point that response detail already contains the request schema so 'full' should not be used just for request fields. That last note directly prevents a likely misuse.

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

Purpose4/5

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

Opens with a specific verb and resource: fetch Cambrian API docs from a named source (docs.cambrian.org/llms.txt). The tool_name guidance ('when you know the exact MCP endpoint tool') implicitly positions it as the documentation lookup alongside the sibling data endpoints, though it never states outright that this is where you go for docs on those siblings.

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?

Explicitly routes between the three selectors: path when you know the path, tool_name when you know the exact MCP tool, query when neither is known. It also states the mutual-exclusion rule ('Send only one of path, tool_name, or query'), the no-argument behavior (concise root directory), and when detail='full' is unnecessary. This is near-complete when/when-not guidance.

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

Deploy Server

Other Tools