DeepSeek MCP Server

chat_completion

Generate single-turn or multi-turn responses with DeepSeek V4. Choose flash or pro models, control thinking, and persist conversation context. Provide a message or full chat history to get AI-generated replies.

Instructions

Primary DeepSeek V4 chat tool for single-turn and multi-turn generation. Defaults to deepseek-v4-flash; use deepseek-v4-pro for higher-capability reasoning. Provide either message (simple single user turn) or messages (full chat history); if both are provided, messages is used. Thinking mode is enabled by DeepSeek by default; pass thinking:{type:"disabled"} for non-thinking mode, and use reasoning_effort:"low"|"high"|"max" when thinking is enabled. Use conversation_id to persist context across calls and clear_conversation=true to reset stored state before sending the next turn. Set include_raw_response=true only for debugging because it returns the full provider payload.

Input Schema

TableJSON Schema

Name	Required	Default
`stop`	No
`model`	No	deepseek-v4-flash
`tools`	No
`top_p`	No
`stream`	No
`message`	No
`user_id`	No
`logprobs`	No
`messages`	No
`thinking`	No
`extra_body`	No
`max_tokens`	No
`temperature`	No
`tool_choice`	No
`top_logprobs`	No
`stream_options`	No
`conversation_id`	No
`response_format`	No
`presence_penalty`	No
`reasoning_effort`	No
`frequency_penalty`	No
`clear_conversation`	No
`include_raw_response`	No

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed2 schema fields changedv0.6.0Aug 21, 2026

changedInput schema / properties / reasoning_effort / enum

Previous value: -[
-  "high",
-  "max"
-]New value: +[
+  "low",
+  "high",
+  "max"
+]

addedInput schema / properties / user_id

Added value: +{
+  "maxLength": 512,
+  "minLength": 1,
+  "pattern": "^[a-zA-Z0-9_-]+$",
+  "type": "string"
+}

Changed32 schema fields changedv0.5.0May 8, 2026

addedInput schema / properties / clear_conversation

Added value: +{
+  "default": false,
+  "type": "boolean"
+}

addedInput schema / properties / conversation_id

Added value: +{
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / extra_body

Added value: +{
+  "additionalProperties": {},
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}

removedInput schema / properties / frequency_penalty / default
```
Removed value: -0.1
```

addedInput schema / properties / include_raw_response

Added value: +{
+  "default": false,
+  "type": "boolean"
+}

addedInput schema / properties / logprobs
```
Added value: +{
+  "type": "boolean"
+}
```
removedInput schema / properties / max_tokens / default
```
Removed value: -8000
```
addedInput schema / properties / message / minLength
```
Added value: +1
```
addedInput schema / properties / messages / items / additionalProperties
```
Added value: +{}
```

addedInput schema / properties / messages / items / properties / content / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

removedInput schema / properties / messages / items / properties / content / type
```
Removed value: -"string"
```
addedInput schema / properties / messages / items / properties / name
```
Added value: +{
+  "type": "string"
+}
```
addedInput schema / properties / messages / items / properties / prefix
```
Added value: +{
+  "type": "boolean"
+}
```
addedInput schema / properties / messages / items / properties / reasoning_content
```
Added value: +{
+  "type": "string"
+}
```

changedInput schema / properties / messages / items / properties / role / enum

Previous value: -[
-  "system",
-  "user",
-  "assistant"
-]New value: +[
+  "system",
+  "user",
+  "assistant",
+  "tool"
+]

addedInput schema / properties / messages / items / properties / tool_call_id
```
Added value: +{
+  "type": "string"
+}
```

addedInput schema / properties / messages / items / properties / tool_calls

Added value: +{
+  "items": {
+    "additionalProperties": {},
+    "propertyNames": {
+      "type": "string"
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

changedInput schema / properties / messages / items / required

Previous value: -[
-  "role",
-  "content"
-]New value: +[
+  "role"
+]

addedInput schema / properties / messages / minItems
```
Added value: +1
```

changedInput schema / properties / model / default

Previous value: -"deepseek-reasoner"New value: +"deepseek-v4-flash"

removedInput schema / properties / presence_penalty / default
```
Removed value: -0
```

addedInput schema / properties / reasoning_effort

Added value: +{
+  "enum": [
+    "high",
+    "max"
+  ],
+  "type": "string"
+}

addedInput schema / properties / response_format

Added value: +{
+  "additionalProperties": {},
+  "properties": {
+    "type": {
+      "enum": [
+        "text",
+        "json_object"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "type"
+  ],
+  "type": "object"
+}

addedInput schema / properties / stop

Added value: +{
+  "anyOf": [
+    {
+      "minLength": 1,
+      "type": "string"
+    },
+    {
+      "items": {
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 16,
+      "minItems": 1,
+      "type": "array"
+    }
+  ]
+}

addedInput schema / properties / stream

Added value: +{
+  "default": false,
+  "type": "boolean"
+}

addedInput schema / properties / stream_options

Added value: +{
+  "additionalProperties": {},
+  "properties": {
+    "include_usage": {
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

removedInput schema / properties / temperature / default
```
Removed value: -0.7
```

addedInput schema / properties / thinking

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "type": {
+      "enum": [
+        "enabled",
+        "disabled"
+      ],
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

addedInput schema / properties / tool_choice

Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "none",
+        "auto",
+        "required"
+      ],
+      "type": "string"
+    },
+    {
+      "additionalProperties": {},
+      "properties": {
+        "function": {
+          "additionalProperties": {},
+          "properties": {
+            "name": {
+              "minLength": 1,
+              "type": "string"
+            }
+          },
+          "required": [
+            "name"
+          ],
+          "type": "object"
+        },
+        "type": {
+          "const": "function",
+          "type": "string"
+        }
+      },
+      "required": [
+        "type",
+        "function"
+      ],
+      "type": "object"
+    }
+  ]
+}

addedInput schema / properties / tools

Added value: +{
+  "items": {
+    "additionalProperties": {},
+    "properties": {
+      "function": {
+        "additionalProperties": {},
+        "properties": {
+          "description": {
+            "type": "string"
+          },
+          "name": {
+            "minLength": 1,
+            "type": "string"
+          },
+          "parameters": {
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string"
+            },
+            "type": "object"
+          },
+          "strict": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "name"
+        ],
+        "type": "object"
+      },
+      "type": {
+        "const": "function",
+        "type": "string"
+      }
+    },
+    "required": [
+      "type",
+      "function"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedInput schema / properties / top_logprobs

Added value: +{
+  "maximum": 20,
+  "minimum": 0,
+  "type": "integer"
+}

removedInput schema / properties / top_p / default
```
Removed value: -1
```

First observedv1.0.0Jan 2, 2026

TDQS

A4.8/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly explains default behavior (model default, thinking mode enabled by default), how to override (thinking:{type:'disabled'}), and side effects (conversation_id persists context, clear_conversation resets state, include_raw_response returns full provider payload). It lacks some details like rate limits or error behavior, but for a chat tool, it covers the key behavioral traits well.

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?

The description is dense but efficient, covering all major usage points in three sentences. It front-loads the core purpose and then lists key option combinations without verbosity. Every sentence adds new information, and the structure flows logically from core usage to advanced options.

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

Completeness5/5

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

Given the tool's complexity (23 params, nested objects, no output schema), the description is remarkably complete. It covers selection of input format, model, thinking mode, context persistence, and debugging. While it doesn't cover every parameter (e.g., stop, tools, response_format), those are standard OpenAI-compatible parameters that the agent can infer from the schema. The description addresses the highest-value decisions for the agent.

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 description coverage is 0%, so the description must compensate for the 23 parameters. It does this excellently by explaining the most important parameters and their interplay: message vs messages, thinking, reasoning_effort, conversation_id, clear_conversation, and include_raw_response. It also clarifies model default choices. This is critical guidance that the raw schema does not provide, making the description highly valuable.

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?

The description clearly identifies this as the primary DeepSeek V4 chat tool for single-turn and multi-turn generation, with a specific verb ('chat'), resource ('DeepSeek V4'), and behavior. It also distinguishes itself from sibling tools by being the primary chat tool, while sibling names like 'completion' and 'create_response' suggest overlap.

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?

The description provides explicit guidance on when to use this tool, including model selection ('defaults to deepseek-v4-flash; use deepseek-v4-pro for higher-capability reasoning'), message format selection ('Provide either message or messages; if both are provided, messages is used'), and optional behaviors like conversation persistence and raw response inclusion. It doesn't explicitly name sibling alternatives, but the guidance is clear and context-rich.

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

Install Server

Other Tools

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/DMontgomery40/deepseek-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server