ACE-MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ACE_MCP_LLM_MODEL | No | LLM model name (e.g., deepseek-reasoner) | |
| ACE_MCP_LOG_LEVEL | No | Log level (default info) | |
| ACE_MCP_AUTO_WATCH | No | Enable auto watch for file changes (default true) | |
| ACE_MCP_BATCH_SIZE | No | Indexing batch size (default 32) | |
| ACE_MCP_LLM_API_KEY | No | LLM API key (required for LLM features) | |
| ACE_MCP_LLM_API_URL | No | LLM API URL (e.g., https://api.deepseek.com/v1/chat/completions) | |
| ACE_MCP_DEFAULT_TOP_K | No | Default top K for search (default 8) | |
| ACE_MCP_EMBEDDING_MODEL | No | Remote embedding model (e.g., text-embedding-3-small) | |
| ACE_MCP_TEXT_EXTENSIONS | No | Comma-separated list of text file extensions (default .java,.js,.jsx,.ts,.tsx,.cs,.py) | |
| ACE_MCP_EXCLUDE_PATTERNS | No | Comma-separated list of exclude patterns (default .git,node_modules,dist,build,target,bin,obj,__pycache__,.venv) | |
| ACE_MCP_MAX_FILE_SIZE_KB | No | Maximum file size in KB (default 1024) | |
| ACE_MCP_EMBEDDING_API_KEY | No | Remote embedding API key | |
| ACE_MCP_EMBEDDING_API_URL | No | Remote embedding API URL (e.g., https://api.openai.com/v1/embeddings) | |
| ACE_MCP_EMBEDDING_PROVIDER | No | Embedding provider: local or remote (default local) | |
| ACE_MCP_QA_MAX_SOURCES_MAX | No | Maximum number of retrieval sources for QA (default 50) | |
| ACE_MCP_MAX_LINES_PER_CHUNK | No | Maximum lines per chunk (default 220) | |
| ACE_MCP_ENABLE_VECTOR_SEARCH | No | Enable vector search (default true) | |
| ACE_MCP_VECTOR_INDEXING_MODE | No | Vector indexing mode: lazy or eager (default lazy) | |
| ACE_MCP_QA_MAX_CONTEXT_TOKENS | No | LLM context token budget for QA (default 6000) | |
| ACE_MCP_SEARCH_PER_FILE_LIMIT | No | Max search results per file (default 2) | |
| ACE_MCP_QA_MAX_SOURCES_DEFAULT | No | Default number of retrieval sources for QA (default 10) | |
| ACE_MCP_SEARCH_FANOUT_MULTIPLIER | No | Search candidate set expansion multiplier (default 3) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
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/0215AndrewFeng/ACE-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server