Log Intelligence MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RRF_K | No | Reciprocal Rank Fusion constant (default 60) | 60 |
| LOG_JSON | No | Set to true for JSON logging | |
| LOG_LEVEL | No | Logging level (e.g. DEBUG, INFO) | |
| EMBED_MODEL | No | Embedding model name (e.g. all-mpnet-base-v2) | |
| SI_DATA_DIR | No | Shared directory for logs, vector store, and metadata. Default is ./si_data | ./si_data |
| DENSE_WEIGHT | No | Weight for dense retrieval in RRF fusion | |
| DEFAULT_TOP_K | No | Default top-k for query_logs | |
| EMBED_BACKEND | No | Embedding backend: auto, sentence-transformers, bedrock, or hashing | auto |
| MCP_HTTP_HOST | No | Host for HTTP transport | |
| MCP_HTTP_PORT | No | Port for HTTP transport (default 8081) | 8081 |
| SPARSE_WEIGHT | No | Weight for sparse retrieval in RRF fusion | |
| CANDIDATE_POOL | No | Number of candidate chunks retrieved before fusion | |
| VECTOR_BACKEND | No | Vector store backend: auto, chroma, or numpy | auto |
| CHUNK_MAX_TOKENS | No | Maximum tokens per chunk (capped at 1600) | 1600 |
| CHUNK_MIN_TOKENS | No | Minimum tokens per chunk | |
| CHUNK_TARGET_TOKENS | No | Target tokens per chunk (approximately 1000) | 1000 |
| CHUNK_OVERLAP_TOKENS | No | Number of tokens of overlap between chunks (~150) | 150 |
| USE_ANTHROPIC_TOKENIZER | No | Set to 1 to use exact Claude token counts |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ingest_ticket_logsA | Parse, semantically chunk, embed, and store all log files for a ticket. Reads raw files the Jira MCP downloaded to |
| query_logsA | Hybrid semantic + keyword (BM25) retrieval of the most relevant log chunks. Combines dense vector similarity with BM25 lexical matching, fused via Reciprocal Rank Fusion. Returns ranked chunks with provenance metadata (source file, line range, time span, levels, trace ids). |
| get_log_statsA | Cheap aggregate stats for a ticket's ingested logs (levels, errors, time span). |
| delete_ticket_logsA | Clean up a ticket after the pipeline completes: remove embeddings and raw files. Deletes the ticket's vectors from the store and (by default) the raw log files the Jira MCP downloaded locally, freeing disk and clearing stale data. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool targets a distinct operation: ingest loads and embeds logs, query retrieves relevant chunks, get_log_stats returns aggregates, and delete removes data. There is no meaningful overlap between the two read tools because one returns ranked search results and the other returns summary statistics.
All tool names follow a clean verb_noun snake_case pattern (ingest_ticket_logs, query_logs, get_log_stats, delete_ticket_logs). Object naming varies slightly between ticket_logs and logs, but this does not break the overall consistency.
Four tools cover the full log-intelligence pipeline for a ticket: ingestion, retrieval, stats, and cleanup. The count is appropriately scoped; every tool earns its place.
The set provides the necessary lifecycle: create/ingest, read via query and stats, and delete/cleanup. Logs are effectively immutable, so an update operation is not a meaningful gap.