Skip to content

History of Architecture Pattern MCP

io.github.olk/architecture-pattern-mcp · Registry status: active

Report data on this entry

Every published change to this entry, most recent first.

Changes
2026-10-10Declared version: 1.1.3 → 1.1.5
2026-10-10Last changed in the registry (raw): 2026-10-08 → 2026-10-09
2026-10-10First listed in the registry (raw): 2026-10-08 → 2026-10-09
2026-10-09Declared version: 1.1.2 → 1.1.3
2026-10-09Last changed in the registry (raw): 2026-09-17 → 2026-10-08
2026-10-09First listed in the registry (raw): 2026-09-17 → 2026-10-08
2026-10-09Connection paths (source structure): {"packages":[{"registryType":"oci","identifier":"docker.io/olkowa/architecture-pattern-mcp:1.1.2","runtimeHint":"docker","transport":"stdio","environment":[{"name":"GENERATOR_API_KEY","description":"API key for the generator LLM (LiteLLM provider).","format":"string","required":true,"secret":true},{"name":"GENERATOR_PROVIDER","description":"LiteLLM provider prefix, e.g. openai, anthropic, openrouter, minimax.","format":"string","required":false,"secret":false},{"name":"GENERATOR_MODEL","description":"Model name, combined as <provider>/<model> via LiteLLM.","format":"string","required":false,"secret":false},{"name":"GENERATOR_BASE_URL","description":"OpenAI-compatible base URL (LiteLLM api_base).","format":"string","required":false,"secret":false},{"name":"PATTERN_DIRECTORY","description":"Directory with *-pattern.json files. The image bakes the 40-pattern catalogue at /app/pattern.","format":"string","required":false,"secret":false},{"name":"EMBEDDER_PROVIDER","description":"Embedding backend for pattern retrieval: tei, openai, ollama, vllm or hosted_vllm.","format":"string","required":false,"secret":false},{"name":"EMBEDDER_BASE_URL","description":"Required: the dense retrieval leg embeds the 40-pattern catalogue during startup warmup and the server refuses to start when the endpoint is unreachable. OpenAI-compatible embeddings endpoint ending in /v1: on the Docker host use http://host.docker.internal:8080/v1 (add --add-host=host.docker.internal:host-gateway on Linux); on a shared Docker network use http://pattern-tei-embed:8080/v1.","format":"string","required":true,"secret":false},{"name":"EMBEDDER_API_KEY","description":"API key for the embedder. Keyless TEI accepts any non-empty value; use 'not-needed' there.","format":"string","required":false,"secret":true},{"name":"RERANKER_BASE_URL","description":"Required: pattern retrieval runs a mandatory TEI cross-encoder rerank. On the Docker host use http://host.docker.internal:8080; on a shared Docker network use http://pattern-tei-rerank:8080.","format":"string","required":true,"secret":false}],"additional_arguments_declared":true}],"remotes":[]} → {"packages":[{"registryType":"oci","identifier":"docker.io/olkowa/architecture-pattern-mcp:1.1.3","runtimeHint":"docker","transport":"stdio","environment":[{"name":"GENERATOR_API_KEY","description":"API key for the generator LLM (LiteLLM provider).","format":"string","required":true,"secret":true},{"name":"GENERATOR_PROVIDER","description":"LiteLLM provider prefix, e.g. openai, anthropic, openrouter, minimax.","format":"string","required":false,"secret":false},{"name":"GENERATOR_MODEL","description":"Model name, combined as <provider>/<model> via LiteLLM.","format":"string","required":false,"secret":false},{"name":"GENERATOR_BASE_URL","description":"OpenAI-compatible base URL (LiteLLM api_base).","format":"string","required":false,"secret":false},{"name":"PATTERN_DIRECTORY","description":"Directory with *-pattern.json files. The image bakes the 40-pattern catalogue at /app/pattern.","format":"string","required":false,"secret":false},{"name":"EMBEDDER_PROVIDER","description":"Embedding backend for pattern retrieval: tei, openai, ollama, vllm or hosted_vllm.","format":"string","required":false,"secret":false},{"name":"EMBEDDER_BASE_URL","description":"Required: the dense retrieval leg embeds the 40-pattern catalogue during startup warmup and the server refuses to start when the endpoint is unreachable. OpenAI-compatible embeddings endpoint ending in /v1: on the Docker host use http://host.docker.internal:8080/v1 (add --add-host=host.docker.internal:host-gateway on Linux); on a shared Docker network use http://pattern-tei-embed:8080/v1.","format":"string","required":true,"secret":false},{"name":"EMBEDDER_API_KEY","description":"API key for the embedder. Keyless TEI accepts any non-empty value; use 'not-needed' there.","format":"string","required":false,"secret":true},{"name":"RERANKER_BASE_URL","description":"Required: pattern retrieval runs a mandatory TEI cross-encoder rerank. On the Docker host use http://host.docker.internal:8080; on a shared Docker network use http://pattern-tei-rerank:8080.","format":"string","required":true,"secret":false}],"additional_arguments_declared":true}],"remotes":[]}
2026-10-09Package identifiers (raw): docker.io/olkowa/architecture-pattern-mcp:1.1.2 → docker.io/olkowa/architecture-pattern-mcp:1.1.3
2026-10-09Package coordinate: oci:docker.io/olkowa/architecture-pattern-mcp:1.1.2 → oci:docker.io/olkowa/architecture-pattern-mcp:1.1.3
2026-09-18Declared version: 1.0.1 → 1.1.2
2026-09-18Required secrets declared: no → yes
2026-09-18Last changed in the registry (raw): 2026-08-14 → 2026-09-17
2026-09-18First listed in the registry (raw): 2026-08-14 → 2026-09-17
2026-09-18Environment variable descriptions (raw): – → EMBEDDER_API_KEY=API key for the embedder. Keyless TEI accepts any non-empty value; use 'not-needed' there. · EMBEDDER_BASE_URL=Required: the dense retrieval leg embeds the 40-pattern catalogue during startup warmup and the server refuses to start when the endpoint is unreachable. OpenAI-compatible embeddings endpoint ending in /v1: on the Docker host use http://host.docker.internal:8080/v1 (add --add-host=host.docker.internal:host-gateway on Linux); on a shared Docker network use http://pattern-tei-embed:8080/v1. · EMBEDDER_PROVIDER=Embedding backend for pattern retrieval: tei, openai, ollama, vllm or hosted_vllm. · GENERATOR_API_KEY=API key for the generator LLM (LiteLLM provider). · GENERATOR_BASE_URL=OpenAI-compatible base URL (LiteLLM api_base). · GENERATOR_MODEL=Model name, combined as <provider>/<model> via LiteLLM. · GENERATOR_PROVIDER=LiteLLM provider prefix, e.g. openai, anthropic, openrouter, minimax. · PATTERN_DIRECTORY=Directory with *-pattern.json files. The image bakes the 40-pattern catalogue at /app/pattern. · RERANKER_BASE_URL=Required: pattern retrieval runs a mandatory TEI cross-encoder rerank. On the Docker host use http://host.docker.internal:8080; on a shared Docker network use http://pattern-tei-rerank:8080.
2026-09-18Environment variable formats (raw): – → string
2026-09-18Connection paths (source structure): {"packages":[{"registryType":"npm","identifier":"@olkow/architecture-pattern-mcp","version":"1.0.1","transport":"stdio","environment":[],"additional_arguments_declared":false}],"remotes":[]} → {"packages":[{"registryType":"oci","identifier":"docker.io/olkowa/architecture-pattern-mcp:1.1.2","runtimeHint":"docker","transport":"stdio","environment":[{"name":"GENERATOR_API_KEY","description":"API key for the generator LLM (LiteLLM provider).","format":"string","required":true,"secret":true},{"name":"GENERATOR_PROVIDER","description":"LiteLLM provider prefix, e.g. openai, anthropic, openrouter, minimax.","format":"string","required":false,"secret":false},{"name":"GENERATOR_MODEL","description":"Model name, combined as <provider>/<model> via LiteLLM.","format":"string","required":false,"secret":false},{"name":"GENERATOR_BASE_URL","description":"OpenAI-compatible base URL (LiteLLM api_base).","format":"string","required":false,"secret":false},{"name":"PATTERN_DIRECTORY","description":"Directory with *-pattern.json files. The image bakes the 40-pattern catalogue at /app/pattern.","format":"string","required":false,"secret":false},{"name":"EMBEDDER_PROVIDER","description":"Embedding backend for pattern retrieval: tei, openai, ollama, vllm or hosted_vllm.","format":"string","required":false,"secret":false},{"name":"EMBEDDER_BASE_URL","description":"Required: the dense retrieval leg embeds the 40-pattern catalogue during startup warmup and the server refuses to start when the endpoint is unreachable. OpenAI-compatible embeddings endpoint ending in /v1: on the Docker host use http://host.docker.internal:8080/v1 (add --add-host=host.docker.internal:host-gateway on Linux); on a shared Docker network use http://pattern-tei-embed:8080/v1.","format":"string","required":true,"secret":false},{"name":"EMBEDDER_API_KEY","description":"API key for the embedder. Keyless TEI accepts any non-empty value; use 'not-needed' there.","format":"string","required":false,"secret":true},{"name":"RERANKER_BASE_URL","description":"Required: pattern retrieval runs a mandatory TEI cross-encoder rerank. On the Docker host use http://host.docker.internal:8080; on a shared Docker network use http://pattern-tei-rerank:8080.","format":"string","required":true,"secret":false}],"additional_arguments_declared":true}],"remotes":[]}
2026-09-18Runtime hints (raw): – → docker
2026-09-18Package versions (raw): 1.0.1 → –
2026-09-18Package identifiers (raw): @olkow/architecture-pattern-mcp → docker.io/olkowa/architecture-pattern-mcp:1.1.2
2026-09-18Package registries (raw): npm → oci
2026-09-18Required secret variables (raw): – → GENERATOR_API_KEY
2026-09-18Environment variables (raw): – → GENERATOR_API_KEY, GENERATOR_PROVIDER, GENERATOR_MODEL, GENERATOR_BASE_URL, PATTERN_DIRECTORY, EMBEDDER_PROVIDER, EMBEDDER_BASE_URL, EMBEDDER_API_KEY, RERANKER_BASE_URL
2026-09-18Package coordinate: npm:@olkow/architecture-pattern-mcp → oci:docker.io/olkowa/architecture-pattern-mcp:1.1.2
2026-09-18Name: io.github.olk/architecture-pattern-mcp → Architecture Pattern MCP
2026-09-08Connection paths (source structure): – → {"packages":[{"registryType":"npm","identifier":"@olkow/architecture-pattern-mcp","version":"1.0.1","transport":"stdio","environment":[],"additional_arguments_declared":false}],"remotes":[]}
2026-08-26Description (raw): – → MCP server that provides architecture design expertise to AI coding agents
2026-08-16Last changed in the registry (raw): – → 2026-08-14
2026-08-16First listed in the registry (raw): – → 2026-08-14
2026-08-16Registry status message (raw): – → –
2026-08-16Schema version of the raw record (raw): – → https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json
2026-08-16Icon formats (raw): – → –
2026-08-16Environment variable descriptions (raw): – → –
2026-08-16Environment variable formats (raw): – → –
2026-08-16Delivery form (raw): – → package
2026-08-16Remote hosts (raw): – → –
2026-08-16Remote URLs (raw): – → –
2026-08-16Runtime hints (raw): – → –
2026-08-16Package versions (raw): – → 1.0.1
2026-08-16Package identifiers (raw): – → @olkow/architecture-pattern-mcp
2026-08-16Repository subfolder (raw): – → –
2026-08-16Repository platform (raw): – → github
2026-08-16Path environment variables (raw): – → –
2026-08-16Required secret headers (raw): – → –
2026-08-15Declared version: – → 1.0.1
2026-08-15Repository URL listed: – → yes
2026-08-15Path argument present: – → no
2026-08-15Execution location: – → local
2026-08-15Required secrets declared: – → no
2026-08-15Package registries (raw): – → npm
2026-08-15Repository (raw): – → https://github.com/olk/architecture-pattern-mcp

This view pages forward and states no total: individual rows are dropped only at output time when their evidence is missing. A counted total would be larger than what is shown.

tracevero · https://tracevero.com/mcp/io-github-olk-architecture-pattern-mcp/aenderungen