architecture-pattern-mcp
by olk
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CONFIG_PATH | No | Path to config file | ~/.config/architecture-pattern-mcp/config.json |
| EMBEDDER_MODEL | No | TEI model name or path | data/qwen3-embedding-0.6b |
| RETRIEVAL_MODE | No | Retrieval fusion mode | reciprocal_rerank |
| GENERATOR_MODEL | No | Model name | gpt-4o-mini |
| EMBEDDER_API_KEY | No | TEI API key (not needed for local TEI) | not-needed |
| EMBEDDER_BASE_URL | No | TEI server URL | http://127.0.0.1:8080/v1 |
| EMBEDDER_PROVIDER | No | Embedder provider (tei or openai) | tei |
| GENERATOR_API_KEY | Yes | API key for the LLM provider | |
| PATTERN_DIRECTORY | No | Directory for pattern JSON files | ~/.config/architecture-pattern-mcp/pattern |
| GENERATOR_BASE_URL | No | API base URL | https://api.openai.com/v1 |
| GENERATOR_PROVIDER | No | LLM provider (openai, minimax, anthropic, etc.) | openai |
| RETRIEVAL_BM25_TOP_K | No | BM25 retrieval count (0 = full corpus, no limit) | 0 |
| GENERATOR_TEMPERATURE | No | LLM sampling temperature | 0.7 |
| RETRIEVAL_DENSE_TOP_K | No | Dense vector retrieval count (0 = full corpus, no limit) | 0 |
| RETRIEVAL_TOP_K_PATTERNS | No | Number of top patterns to retrieve | 5 |
| RETRIEVAL_MIN_QUALITY_SCORE | No | Early-stop quality threshold | 50.0 |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
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/olk/architecture-pattern-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server