abstract-backend-mcp
by marmillas
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CONFIG_FILE | No | Path to YAML config file (also via --config) | |
| ENVIRONMENT | No | Current environment | development |
| MONGODB_URI | No | MongoDB connection string | mongodb://localhost:27017 |
| PROJECT_NAME | No | Project identifier | my-project |
| FASTAPI_APP_PATH | No | Python import path of the FastAPI app | app.main:app |
| MAX_OUTPUT_ITEMS | No | Max items returned by paginated Stackraise tools | 50 |
| ENABLE_FASTAPI_TOOLS | No | Enable FastAPI tools | true |
| ENABLE_MONGODB_TOOLS | No | Enable MongoDB tools | true |
| ALLOW_WRITE_OPERATIONS | No | Allow MongoDB writes | false |
| MAX_SOURCE_CHUNK_LINES | No | Max lines returned by source-oriented tools | 200 |
| ENABLE_STACKRAISE_TOOLS | No | Enable Stackraise tools | false |
| REDACT_SENSITIVE_FIELDS | No | Redact secrets in all output | true |
| STACKRAISE_CONTEXT_MODE | No | Extraction mode: static, runtime, hybrid | hybrid |
| STACKRAISE_MODULE_ROOTS | No | Optional glob roots for Stackraise packages | [] |
| MAX_TOTAL_SNAPSHOT_ITEMS | No | Global cap for deep snapshot inventories | 500 |
| MONGODB_SAMPLE_MAX_BYTES | No | Maximum total bytes returned by sample_documents | 65536 |
| ALLOWED_WRITE_COLLECTIONS | No | Collection allowlist (empty = all) | [] |
| PROJECT_INSTRUCTIONS_FILE | No | Path to project instructions file | PROJECT.md |
| REQUIRE_WRITE_CONFIRMATION | No | Require explicit confirmed=True | true |
| MONGODB_SAMPLE_MAX_DOCUMENTS | No | Maximum number of sampled documents returned by MongoDB tools | 20 |
| STACKRAISE_SEARCH_TIMEOUT_MS | No | Search timeout budget in milliseconds | 500 |
| ALLOW_FASTAPI_RUNTIME_IMPORTS | No | Allow importing FastAPI runtime app for route/OpenAPI inspection | false |
| ALLOW_RUNTIME_CONTEXT_IMPORTS | No | Allow live runtime imports during context extraction | false |
| ENABLE_DEEP_STACKRAISE_CONTEXT | No | Enable deep module/symbol indexing | true |
| MONGODB_SAMPLE_MAX_FIELD_CHARS | No | Max characters preserved per string field in sampled documents | 2000 |
| STACKRAISE_SEARCH_MAX_SCANNED_LINES | No | Max total scanned lines for code search | 20000 |
| STACKRAISE_CONTEXT_CACHE_MAX_ENTRIES | No | Max in-memory context cache entries | 32 |
| STACKRAISE_CONTEXT_CACHE_TTL_SECONDS | No | Cache TTL for Stackraise context provider | 30 |
| STACKRAISE_SEARCH_MAX_PATTERN_LENGTH | No | Max accepted length for search_stackraise_code pattern | 200 |
| STACKRAISE_CONTEXT_FINGERPRINT_TTL_SECONDS | No | TTL for project fingerprint reuse before rescanning files | 1 |
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
- 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/marmillas/stackraise-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server