// MCP TOOL REFERENCE

DEEPSEEK TOOLS

15 tools from the Deepseek MCP Server, categorised by risk level.

// ALL 15 DEEPSEEK TOOLS

READ 4 tools

Read content Message text content Read cost_comparison Compare LLM costs for different tasks Read role Message role (system, user, assistant, tool) Read Type-Safe Full TypeScript implementation

EXECUTE 11 tools

Execute argument_validation Analyse arguments for logical fallacies Execute code_review_deep Review code for security, performance, and quality Execute create_function_schema Generate JSON Schema for function calling Execute creative_ideation Generate creative ideas with feasibility analysis Execute debug_with_reasoning Debug code with step-by-step DeepSeek analysis Execute explain_like_im_five Explain complex topics in simple terms via DeepSeek Execute function_call_debug Debug function calling issues via DeepSeek Execute mathematical_proof Prove mathematical statements via DeepSeek Execute pair_programming Interactive coding assistance via DeepSeek Execute research_synthesis Research topics and create structured reports Execute strategic_planning Create strategic plans with reasoning analysis

// RUNNING THIS SERVER

The managed route: connect Deepseek through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @arikusi/deepseek-mcp-server

// FAQ

How many tools does the Deepseek MCP server have? +

The Deepseek MCP server exposes 15 tools across 2 categories: Read, Execute.

How do I enforce policies on Deepseek tools? +

Route the Deepseek server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Deepseek tools fall into? +

Deepseek tools are categorised as Read (4), Execute (11). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.