DeepSeek-MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Log level | |
| MAX_RETRIES | No | Maximum retries | |
| DEEPSEEK_API_KEY | Yes | Your DeepSeek API key | |
| DEFAULT_PROVIDER | No | Default LLM provider | |
| DEEPSEEK_BASE_URL | No | Base URL for DeepSeek API | |
| DEFAULT_TIMEOUT_MS | No | Default timeout in milliseconds | |
| MAX_PARALLEL_TASKS | No | Maximum number of parallel tasks | |
| DEEPSEEK_REASONING_EFFORT | No | Reasoning effort level | |
| DEEPSEEK_DEFAULT_CHAT_MODEL | No | Default chat model | |
| DEEPSEEK_DEFAULT_REASONER_MODEL | No | Default reasoner model |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| review_codeA | Review a single file or code snippet for bugs, quality, and best practices using DeepSeek |
| review_folderB | Review multiple files within a folder to analyze relationships and module code quality |
| review_projectC | Perform a comprehensive high-level project review utilizing DeepSeek Reasoner model |
| review_sqlB | Review SQL queries, table schemas, database migrations, and index performance |
| review_architectureA | Analyze system architecture, design patterns, scalability, and coupling bottlenecks using Reasoner LLM |
| review_securityA | Perform a deep cybersecurity audit focusing on OWASP vulnerabilities, secret leaks, and access control |
| review_performanceA | Identify performance bottlenecks, memory leaks, algorithmic complexity (Big O), and async I/O overhead |
| write_testsB | Generate high-coverage unit or integration tests for the provided code |
| generate_seedA | Generate realistic mock data / seed fixtures for database tables or API payloads |
| summarizeA | Summarize complex codebases, documentations, or technical specifications |
| documentationC | Generate clean technical Markdown documentation for APIs, classes, or modules |
| analyze_repositoryC | Analyze repository directory structure, key dependencies, and high-level architectural design |
| explain_codeB | Explain step-by-step how a specific complex piece of code works |
| refactor_codeB | Provide refactored version of code adhering to Clean Code, SOLID principles, and optimal patterns |
| generate_codeA | Generate a brand-new single file (Repository, Service, Controller, DTO, Entity, Validator, Middleware, Background Job, Migration, Stored Procedure, View, Interface, Extension, Configuration, etc.) from a specification using DeepSeek. Returns structured, saveable file content — never writes to disk itself. |
| generate_filesA | Generate several related files in one call (e.g. a full module: interface + implementation + DTOs + validators + mapper + controller). Returns structured, saveable file content — never writes to disk itself. |
| generate_sqlA | Generate SQL objects — stored procedures, views, functions, triggers, migrations, indexes — from a specification. Returns structured, saveable file content — never writes to disk itself. |
| generate_testsA | Generate a full, saveable test-suite (unit/integration/performance) as file(s) from a specification or existing code — distinct from write_tests, which returns inline review-style test code. Returns structured, saveable file content — never writes to disk itself. |
| generate_documentationA | Generate a full, saveable documentation set (README, API docs, architecture docs, Mermaid sequence diagrams) as file(s) — distinct from documentation, which returns inline Markdown for a single piece of content. Returns structured, saveable file content — never writes to disk itself. |
| generate_projectA | Generate a full project scaffold under a named architecture (Clean Architecture, Onion, Vertical Slice, Modular Monolith, Microservices, CQRS, Repository+UoW). Recommended for small-to-medium scaffolds in one call; for large projects call generate_files repeatedly per module instead of expecting one call to build an entire system. Returns structured, saveable file content — never writes to disk itself. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/Abbas-F-R/DeepSeek-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server