Skip to main content
Glama
deepseek-mcp-server

deepseek-mcp-server

DeepSeek fill-in-the-middle

deepseek_fim

Complete code between a prompt and suffix to fill function bodies or finish partial blocks for inline code completion; returns only the completion, with no chat commentary.

Instructions

Fill-in-the-middle completion against the DeepSeek beta endpoint. Give the code before the cursor as prompt and the code after it as suffix; the model writes the middle. This is the right tool for inline code completion, filling a function body, or finishing a partial block - it is not a chat call and returns no commentary.

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": {
      "prompt": "<prompt>"
    },
    "name": "deepseek_fim"
  }
}

Input Schema

NameRequiredDescriptionDefault
echoNoEcho the prompt back with the completion.
stopNo
extraNo
modelNoDefaults to deepseek-chat.
top_pNo
promptYesCode before the insertion point.
streamNo
suffixNoCode after the insertion point. Omit for a plain continuation.
logprobsNo0-20 log probabilities per token.
max_tokensNoMax tokens to generate.
timeout_msNo
temperatureNo
raw_responseNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It usefully discloses that this hits a beta endpoint and returns code without commentary, but says nothing about streaming, the echo/raw_response behaviors, or what happens when required input is malformed.

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

Conciseness5/5

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

Three sentences with no wasted words, front-loaded with purpose and the prompt/suffix model before the usage guidance. Every sentence adds something.

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

Completeness3/5

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

For a 13-parameter tool with a nested object, no annotations, and no output schema, the description covers the core calling pattern but leaves streaming, echo, and most tuning parameters unexplained. It is adequate to invoke the basic case but incomplete for the full surface.

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

Parameters2/5

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

Schema coverage is only 46% and roughly nine parameters (echo, stop, extra, stream, logprobs, temperature, timeout_ms, raw_response, top_p) are undocumented everywhere. The description explains prompt/suffix, but that largely repeats the schema's own field descriptions, so it does not compensate for the coverage gap.

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 (fill-in-the-middle completion on the DeepSeek beta endpoint) and immediately contrasts it with a chat call, so an agent can tell it apart from the deepseek_chat sibling without opening either 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?

Gives concrete when-to-use cases (inline code completion, filling a function body, finishing a partial block) and an explicit exclusion (not a chat call). It stops short of naming an alternative tool outright, but the chat exclusion is enough to route most calls correctly.

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