fittok
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FITTOK_MODEL | No | CPU model name for LLMLingua compression | bert-base-multilingual |
| FITTOK_SCRUB | No | Enable PII scrubbing in pipeline (true/false) | false |
| FITTOK_DEVICE | No | Device to use: auto, cuda, cpu | auto |
| FITTOK_CACHE_DIR | No | Cache directory path | ~/.cache/fittok |
| FITTOK_MODEL_GPU | No | GPU model name for LLMLingua compression | bert-base-multilingual |
| FITTOK_CACHE_MAX_MB | No | Maximum cache size in MB | 500 |
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 |
|---|---|
| parse_codebase_toolC | Parse all code files in a directory into a knowledge graph. |
| query_graph_toolC | Query a knowledge graph for the most relevant subgraph within a token budget. |
| compress_context_toolD | Compress text context using LLMLingua with a local model. |
| optimize_context_toolA | Return the most relevant REAL source code for a question, within a token budget. Use this FIRST for any "how does X work / where is Y" question about the
codebase, and prefer it over reading files or grepping. Call it ONCE per
question: the returned |
| optimize_context_streamC | Streaming pipeline: yields stage-by-stage progress events. Returns a list of event dicts in order: [{"stage": "parsing", "status": "started"}, ...] |
| optimize_context_batchC | One parse, many queries. Builds graph once, runs slurp+compress per query. |
| optimize_context_structuredD | Full pipeline with structured JSON output mode. Args: output_format: "markdown" (default) or "json" for structured output. |
| parse_codebase_stream_toolC | Stream parse progress. Parses in batches, returns progress events. |
| watch_start_toolC | Start watching a codebase for incremental graph updates. |
| watch_stop_toolC | Stop watching a codebase. |
| get_graph_stats_toolC | Return metadata and stats for a graph. |
| reset_graph_toolC | Force a full re-parse of the codebase, ignoring cache. |
| diff_graph_toolC | Compare two knowledge graphs and return structural differences. |
| scrub_text_toolC | Scrub PII (secrets, emails, API keys, etc.) from text. |
| scrub_file_toolC | Scrub PII from a file. |
| list_pii_patterns_toolA | List all registered PII detection patterns. |
| add_pii_pattern_toolC | Add or override a PII detection pattern. |
| clear_cache_toolB | Clear the cache. Scope: 'all' | 'graph' | 'query' | 'compression'. |
| cache_stats_toolB | Return cache hit/miss statistics and size. |
| launch_ui_toolC | Launch the web visualization UI for graph exploration. |
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 20 tools
Most tools have distinct purposes, with PII, cache, graph, and context optimization groups clearly separated. However, the optimize_context_* series (batch, stream, structured, tool) may cause confusion as they all relate to context optimization with different modes, but detailed descriptions help differentiate.
Most tools use snake_case with '_tool' suffix (e.g., add_pii_pattern_tool, clear_cache_tool), but several like optimize_context_batch, optimize_context_stream, and optimize_context_structured lack the suffix, creating inconsistency.
20 tools cover a complex domain including parsing, caching, PII, context optimization, graph queries, and UI. While on the higher side, each tool serves a specific function and the count is appropriate for the server's scope.
The tool set covers major operations like parsing, querying, caching, and PII scrubbing. However, missing operations such as deleting a PII pattern or explicitly deleting a graph (only reset exists) leave minor gaps in lifecycle management.