Skip to main content
Glama
anands-bounteous

Log Intelligence MCP

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RRF_KNoReciprocal Rank Fusion constant (default 60)60
LOG_JSONNoSet to true for JSON logging
LOG_LEVELNoLogging level (e.g. DEBUG, INFO)
EMBED_MODELNoEmbedding model name (e.g. all-mpnet-base-v2)
SI_DATA_DIRNoShared directory for logs, vector store, and metadata. Default is ./si_data./si_data
DENSE_WEIGHTNoWeight for dense retrieval in RRF fusion
DEFAULT_TOP_KNoDefault top-k for query_logs
EMBED_BACKENDNoEmbedding backend: auto, sentence-transformers, bedrock, or hashingauto
MCP_HTTP_HOSTNoHost for HTTP transport
MCP_HTTP_PORTNoPort for HTTP transport (default 8081)8081
SPARSE_WEIGHTNoWeight for sparse retrieval in RRF fusion
CANDIDATE_POOLNoNumber of candidate chunks retrieved before fusion
VECTOR_BACKENDNoVector store backend: auto, chroma, or numpyauto
CHUNK_MAX_TOKENSNoMaximum tokens per chunk (capped at 1600)1600
CHUNK_MIN_TOKENSNoMinimum tokens per chunk
CHUNK_TARGET_TOKENSNoTarget tokens per chunk (approximately 1000)1000
CHUNK_OVERLAP_TOKENSNoNumber of tokens of overlap between chunks (~150)150
USE_ANTHROPIC_TOKENIZERNoSet 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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
ingest_ticket_logsA

Parse, semantically chunk, embed, and store all log files for a ticket.

Reads raw files the Jira MCP downloaded to <data_dir>/logs/<ticket_id>/ (or an explicit paths list). Chunks are entry-aware and token-budgeted for Claude Sonnet/Opus. Returns ingestion stats including token distribution.

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

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.3/5.0

Scored across 4 tools

Disambiguation5/5

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.

Naming Consistency5/5

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.

Tool Count5/5

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.

Completeness5/5

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.

Maintenance

ActivityMaintained
ResponsivenessNo issues