Mullet
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KIMI_API_KEY | No | Moonshot API key for Kimi K2 (primary delegation target). Optional — skip and use a local LLM via Ollama / LM Studio instead. | |
| TRAWL_POOLS_DIR | No | Directory where Mullet stores indexed code/document pools (vector + graph DBs). If set, overrides the default ~/.mullet/pools/ location. | |
| ANTHROPIC_API_KEY | No | Anthropic API key for direct Anthropic routing only (pay-per-token, orchestrator tier). Not needed when using Mullet via Claude Code, which handles Anthropic access natively through your subscription. | |
| OPENROUTER_API_KEY | No | OpenRouter API key — provides access to 8 curated models via an OpenAI-compatible API. |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mullet_runA | For code editing tasks (reading/modifying files), use mullet_opencode instead: it runs the edit as a gated Mullet job and applies the result to the working tree only after the gates pass. Use mullet_run only for: analysis, planning, research, review, or text generation tasks where no files need to be written. Routes to the optimal provider (local GPU or cloud) based on complexity. |
| mullet_delegateA | Delegate a subtask to a Mullet child agent. The child runs independently with its own context and tools, routed by complexity. |
| mullet_statusA | Check Mullet's current status — active tasks, provider health, budget. |
| mullet_providersA | List available LLM providers and their health status. |
| mullet_searchC | Search project knowledge for relevant context. Uses Trove's hybrid search engine. |
| mullet_rememberC | Store a memory in a project's knowledge base for future sessions. |
| mullet_analyzeA | Analyze a task's complexity and show what provider/tier the router would select. Useful for understanding routing decisions. |
| mullet_budgetB | Query current token spend and budget limits. |
| mullet_opencodeA | PREFERRED for code editing tasks. Runs the task as a single gated Mullet job on the delegation ladder (the cheapest worker that can pass the project's gates does the work) and applies the result to the working tree only after the gates pass. Changes are left unstaged and are never committed or pushed. Returns JSON with status (applied, passed_not_applied, failed, blocked, unverified or timeout), job id, report path, rung, model, cost, gate summary and files changed. |
| mullet_swarmB | Fan-out a goal across many Kimi K2 calls in parallel and synthesize the results. Use for tasks that can be split across multiple files, items, or independent sub-questions. |
| trawl_list_poolsA | List all available knowledge pools. Each client has its own indexed document collection. |
| trawl_load_poolB | Load a specific pool for subsequent searches. |
| trawl_graph_pruneA | Remove orphaned entities, relationships, and processed-chunk tracking whose source chunks no longer exist in the collection. |
| trawl_get_poolC | Get information about the currently loaded pool. |
| trawl_pool_deleteA | Permanently delete a Trawl pool (directory + index). Requires confirm=true. |
| trawl_searchB | Search across all indexed documents using hybrid BM25 + vector search. |
| trawl_search_poolC | One-shot search: load a client and search in one call. |
| trawl_recentA | List a pool's documents newest first, by the best date known for each: a page's own published date, a PDF's creation date, when the web crawler first saw it, or when its text last changed. Use this, not search, for 'what's new' / 'recent news' questions. |
| trawl_search_codeC | Search code specifically with language and symbol type filters. |
| trawl_search_multiB | Search across multiple clients with reciprocal rank fusion. Omit clients to search all. |
| trawl_find_symbolB | Find a specific code symbol (function, class, variable) by name. |
| trawl_reindex_poolB | Trigger a full reindex of a client's documents. Runs in the background. |
| trawl_sync_poolB | Incremental reindex — only process new/modified files since last index. Fast. |
| trawl_ingest_statusC | Check the status of an ingestion job. |
| trawl_ingest_fileC | Ingest a single file into a pool.s collection. |
| trawl_ingest_urlC | Ingest content from a URL into a pool.s collection. |
| trawl_memory_storeC | Store a memory/note with semantic search capability. |
| trawl_memory_searchC | Search stored memories semantically. |
| trawl_memory_listB | List all stored memories, optionally filtered by namespace. |
| trawl_memory_deleteB | Delete a memory by namespace and key. |
| trawl_build_graphB | Build or rebuild the knowledge graph for a client. Runs in background. |
| trawl_graph_statsB | Get knowledge graph statistics (node/edge counts, entity types). |
| trawl_search_entitiesC | Search for entities in the knowledge graph. |
| trawl_search_relationshipsC | Search for relationships between entities in the knowledge graph. |
| trawl_list_sourcesC | List document sources for a client. |
| trawl_sync_sourcesC | Sync all sources for a client (pull latest from git repos, etc.). |
| trawl_connect_githubC | Add a GitHub account, org, or repo as a source for a pool. |
| trawl_crawl_webC | Crawl a website and save pages as Markdown for a client. |
| trawl_summarizeC | Search and return concise summaries of results using LLM. |
| trawl_list_reposC | List GitHub repos indexed for a client. |
| trawl_search_repoC | Search within a specific repository. |
| trawl_graph_exportB | Export knowledge graph as D3.js-compatible JSON for visualization. |
| trawl_workflow_createC | Create a workflow with named steps and dependency ordering. |
| trawl_workflow_statusB | Get workflow status and step progress. |
| trawl_workflow_updateC | Update a workflow step's status. |
| trawl_workflow_listB | List all workflows, optionally filtered by status. |
| trawl_agents_listB | List available agent templates, optionally filtered by tag. |
| trawl_agents_getB | Get full agent template config including system prompt. |
| trawl_run_agentC | Run a Trove agent with local LLM — searches context, applies agent prompt, generates response. |
| trawl_prompts_search_liveC | Search the prompts.chat API for prompt templates. |
| trawl_prompts_findB | Find prompts by combining local index and live API search. |
| trawl_prompts_getB | Get a specific prompt template by ID with optional variable substitution. |
| trawl_docs_lookupA | Look up documentation for a library using Context7 (version-aware) with fallback to local Trawl pools. Use this when you need API docs, usage examples, or version-specific information for any library. |
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 53 tools
Several tools have overlapping search and memory purposes: mullet_search, trawl_search, trawl_search_pool, trawl_search_multi, trawl_summarize, mullet_remember, and trawl_memory_* all compete for similar retrieval/storage intents. Execution tools also blur together: mullet_run, mullet_opencode, mullet_delegate, mullet_swarm, and trawl_run_agent all perform routed LLM work with subtle boundary distinctions that an agent must parse carefully.
The mullet_ and trawl_ prefixes provide a useful top-level grouping, and all names are snake_case. However, within trawl the convention is mixed: some tools use action_resource order (trawl_search_entities, trawl_get_pool, trawl_load_pool) while others use resource_action order (trawl_agents_list, trawl_pool_delete, trawl_memory_store, trawl_workflow_create).
At 53 tools, the surface is very large and heavy for a single server, spanning orchestration, search, ingestion, graph operations, memory, workflows, agents, prompts, and docs. While these are related platform capabilities, the count far exceeds a well-scoped set and increases selection burden.
The surface covers many lifecycle operations, including memory store/search/list/delete, workflow create/list/status/update, pool management, ingestion, graph build/stats/export, agents, prompts, and docs lookup. But there are notable gaps such as no clear entity or relationship update/delete beyond graph pruning, no task cancellation or explicit active-task listing, and limited update/delete coverage for prompts and agents.