Skip to main content
Glama
deepseek-mcp-server

deepseek-mcp-server

Raw DeepSeek API request

deepseek_raw_request

Sends a custom request to any DeepSeek API endpoint and returns unmodified JSON, covering endpoints or parameters not modeled by typed tools.

Instructions

Call any DeepSeek API endpoint directly with a body you control, and get the unmodified JSON back. This is the unrestricted escape hatch: it covers endpoints and parameters that the typed tools above do not model, including anything DeepSeek adds after this server was written. Authentication, retries, timeouts and base-URL resolution are still handled for you. Examples: path '/chat/completions' with your own body, path '/models' with method GET, path '/completions' with beta true.

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": {
      "path": "<path>"
    },
    "name": "deepseek_raw_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
betaNoSend to the beta base URL (https://api.deepseek.com/beta) instead of the stable one.
bodyNoJSON request body, sent verbatim.
pathYesEndpoint path, e.g. /chat/completions, /models, /user/balance, /completions
queryNoQuery-string parameters.
methodNoHTTP method. Default POST.
streamNoTreat the response as SSE and return the assembled result.
headersNoAdditional request headers.
timeout_msNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the load and does well: it discloses that auth, retries, timeouts, and base-URL resolution are handled by the server, that responses come back unmodified, and that beta routes go to a different base URL. It does not address error/non-2xx handling or the side effects of arbitrary mutating methods like DELETE, which is the main remaining gap for an escape hatch.

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-loaded with purpose and the escape-hatch framing before the operational details, and every sentence carries information (what it does, when to use it, what is handled for you, examples). The examples sentence is dense but justified for an 8-parameter tool; minor tightening is possible but nothing is filler.

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 an 8-parameter, unannotated, no-output-schema tool with nested objects, the description covers the essentials: verb, escape-hatch scope, managed concerns, and return shape. Gaps remain around failure behavior, streaming semantics beyond 'assembled result', and the practical reach of non-POST methods, but nothing critical to a correct invocation is missing.

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

Parameters4/5

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

Schema coverage is already 88%, so the baseline is 3; the description adds real meaning by showing how path, body, method, and beta combine ('/chat/completions' with your own body, '/models' with method GET, '/completions' with beta true). It adds no guidance on timeout_ms or headers, so it improves on the schema rather than fully substituting for it.

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 and resource ('Call any DeepSeek API endpoint directly... get the unmodified JSON back') and immediately positions itself as the 'unrestricted escape hatch' versus the typed tools. An agent can distinguish it from deepseek_chat, deepseek_fim, or deepseek_models 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 Guidelines4/5

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

Explicitly says to use it for endpoints/parameters the typed tools do not model, which implies the converse (prefer typed tools when they cover the case) and includes concrete path examples for each mode. It stops short of naming a specific sibling to prefer or stating hard exclusions, so it is clear context rather than a full routing rule.

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