Skip to main content
Glama
deepseek-mcp-server

deepseek-mcp-server

DeepSeek file and codebase analysis

deepseek_analyze_files

Reads local files, directories, or globs and asks DeepSeek a question about them for codebase Q&A, cross-file review, config auditing, log analysis, or document summarisation.

Instructions

Read local files, directories or globs and ask DeepSeek a question about them. Directories are walked recursively, skipping node_modules, .git, build output and binaries. Use this for codebase questions, cross-file review, config auditing, log analysis or document summarisation. Reads are enabled by default with no path restriction; set DEEPSEEK_FS_ROOTS to confine it or DEEPSEEK_ALLOW_FS=0 to disable reads entirely.

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": {
      "paths": "<paths>"
    },
    "name": "deepseek_analyze_files"
  }
}

Input Schema

NameRequiredDescriptionDefault
stopNoUp to 16 stop sequences. A single string is also accepted.
extraNoArbitrary extra request-body fields, merged last so they override everything else. The escape hatch for any API parameter this server does not model yet.
modelNoOverride the model id for this call.
pathsYesAbsolute or relative file paths, directories, or globs such as src/**/*.ts
toolsNoFunction-calling definitions, passed to the API verbatim. Each item is { type: 'function', function: { name, description, parameters } }.
top_pNoNucleus sampling, 0-1. Ignored by deepseek-reasoner.
streamNoStream from the API and return the assembled result. Useful for very long outputs that would otherwise hit an idle timeout.
systemNo
logprobsNoReturn log probabilities. deepseek-chat only.
questionNoWhat you want to know about these files.
json_modeNoShorthand for response_format { type: 'json_object' }. Your prompt must mention JSON and should show an example.
list_onlyNoReport which files would be sent, with sizes, and make no API call. Use this first on a large tree.
max_depthNoDirectory recursion depth. Default 8.
max_tokensNoMaximum output tokens. Omit for the server-side maximum (8192 for deepseek-chat, 65536 for deepseek-reasoner). No client-side cap is applied.
session_idNoConversation key. Prior turns under this id are prepended automatically and this turn is appended, giving true multi-turn memory across tool calls.
timeout_msNoPer-call timeout override in milliseconds.
temperatureNo0.0-2.0. DeepSeek's own guidance: 0.0 for code and maths, 1.0 for general conversation and data analysis, 1.3 for creative writing. Ignored by deepseek-reasoner.
tool_choiceNo'auto', 'none', 'required', or { type: 'function', function: { name } }.
raw_responseNoReturn the complete unmodified API JSON instead of formatted text.
top_logprobsNo0-20, requires logprobs. deepseek-chat only.
use_reasonerNoRoute to deepseek-reasoner for deep multi-step analysis instead of deepseek-chat.
include_usageNoAppend the token-usage and cache-hit footer. Default true.
max_bytes_totalNoTotal byte budget. 0 for unlimited. Default 8,000,000.
presence_penaltyNo-2.0 to 2.0. Ignored by deepseek-reasoner.
frequency_penaltyNo-2.0 to 2.0. Ignored by deepseek-reasoner.
include_reasoningNoInclude the chain-of-thought block in the result. Default true for deepseek-reasoner.
max_bytes_per_fileNoPer-file byte cap. 0 for unlimited. Default 2,000,000.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does reasonably well: it discloses recursive directory walking, the default skip list (node_modules, .git, build output, binaries), that reads are on by default with no path restriction, and the DEEPSEEK_FS_ROOTS / DEEPSEEK_ALLOW_FS controls. It does not say what is returned, what happens on unreadable or oversized files, or whether the assembled output streams by default.

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?

Four sentences, front-loaded with the core action, followed by traversal behavior, usage contexts, and the read-permission model. No sentence is redundant and nothing important is buried mid-paragraph.

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 27-parameter tool with no annotations and no output schema, the description covers the primary path/permission behavior but says nothing about the shape of the result (formatted text vs. raw JSON via raw_response, reasoning blocks, usage footer). The 96% schema coverage compensates for most individual parameters, but the overall call-and-return picture is only partially described.

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 96%, so nearly every parameter is already documented, including budgets, model routing, session memory, and streaming. The description adds only the path-recursion/skip semantics, which is marginal value over the schema; the 3 baseline applies.

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?

The first sentence states a specific verb (read) and resource (local files/directories/globs) plus the secondary action (ask DeepSeek a question about them). That is enough to separate it from deepseek_chat or deepseek_code, though it never explicitly names or contrasts 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 Guidelines4/5

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

It gives concrete use cases (codebase questions, cross-file review, config auditing, log analysis, document summarisation) and adds a procedural hint inside the schema ('Use this first on a large tree' for list_only). It stops short of stating when another sibling tool would be the better choice.

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