Skip to main content
Glama
deepseek-mcp-server

deepseek-mcp-server

DeepSeek chat (V3)

deepseek_chat

Send prompts to DeepSeek's general-purpose chat model for multi-turn conversations, JSON output, function calling, and streaming responses.

Instructions

Send a prompt to deepseek-chat, DeepSeek's fast general-purpose model. Supports the full API surface: system prompts, multi-turn message arrays, sampling controls, stop sequences, JSON mode, function calling, logprobs, streaming, persistent sessions, and an extra escape hatch for any parameter not modelled here. No client-side token or length caps.

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": "deepseek_chat"
  }
}

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.
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.
promptNoThe user message. Use this for one-shot calls.
streamNoStream from the API and return the assembled result. Useful for very long outputs that would otherwise hit an idle timeout.
systemNoSystem instruction.
logprobsNoReturn log probabilities. deepseek-chat only.
messagesNoFull message array, OpenAI-compatible. Use this instead of `prompt` when you need multi-turn control. Roles: system, user, assistant, tool.
json_modeNoShorthand for response_format { type: 'json_object' }. Your prompt must mention JSON and should show an example.
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.
include_usageNoAppend the token-usage and cache-hit footer. Default true.
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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.6/5.0
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 does add real behavioral facts beyond the title, notably "No client-side token or length caps" and that streaming returns an assembled result. It omits cost/auth/permission expectations, rate limits, and error behavior, which matter for a network-backed LLM call.

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?

Three sentences, front-loaded with the model identity and followed by a capability enumeration; every phrase maps to real functionality. The single long capability list is dense but earns its place as a surface overview.

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 22-parameter, nested-object tool with no annotations and no output schema, the description does well to enumerate the whole supported surface and to flag the `extra` override hatch and the absence of client-side caps. It stops short of describing what a call returns (formatted text vs. raw JSON) or session persistence semantics, which the schema only partially covers.

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 100%, so the baseline is 3, but the description adds value by grouping the parameter surface into capabilities (system prompts, multi-turn arrays, sampling controls, stop sequences, JSON mode, function calling, logprobs, streaming, sessions, `extra` escape hatch). That gives an agent a mental map of what the 22 parameters can do before reading each one.

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 description gives a specific verb and resource ("Send a prompt to deepseek-chat") and characterizes the model as "fast general-purpose," which implicitly distinguishes it from reasoner/code/FIM siblings without naming them. An agent can tell what this tool is, though explicit routing against deepseek_code and deepseek_reason is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage context is implied by "general-purpose model," but there is no explicit when-to-use/when-not statement and no routing guidance toward deepseek_reason, deepseek_code, or deepseek_fim. The choice between `prompt`, `messages`, and `session_id` is clarified only in the schema, not the description.

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