Skip to main content
Glama
valentil

FeatureBoard MCP Server

by valentil

Local lexical RAG search

rag_search
Read-only

Retrieve relevant context from project documents, code documentation, and completed tickets using hybrid BM25 and local embeddings or lexical search.

Instructions

FBMCPF-264/315: local retrieval over this board's KB docs (incl. research briefs), the code repo's docs/ + root README, and Done tickets' title+completionSummary — zero model tokens. Two-stage HYBRID by default: BM25 preselects candidates, a LOCAL embedding model (Xenova/all-MiniLM-L6-v2 via the optional @xenova/transformers dependency; ~25MB model auto-downloaded ONCE on first semantic query, then cached and offline forever) re-ranks by cosine similarity, reciprocal-rank fusion blends the two. Response carries mode: "hybrid" or "lexical" — it falls back to pure BM25 (identical to the old behavior) whenever the optional dep isn't installed, FEATUREBOARD_NO_SEMANTIC=1, or embedding fails, with a note saying why. Pass mode:"lexical" to skip embeddings deliberately (deterministic/offline runs).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kNoHow many chunks to return (default 5, max 20).
modeNohybrid (default): BM25 + local embeddings when available. lexical: BM25 only, no model, fully deterministic.hybrid
queryYesWhat to retrieve context for.
projectYes
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description provides rich behavioral details beyond the annotations, including model caching, offline usage, fallback reasons, and mode behavior. It does not contradict any annotations and adds context that helps the agent understand the tool's behavior in various conditions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is mostly concise, with each sentence contributing to understanding the tool. It is front-loaded with purpose and mode details, though it could be slightly shortened without losing key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is complex with nuanced behavior, and the description covers mode selection and fallback. However, without an output schema, the return value shape (e.g., fields in chunks) is not specified, leaving a gap for the agent to infer.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75% (3 of 4 parameters have descriptions). The description adds extra context for the 'mode' parameter by explaining its implications, but does not significantly enhance understanding of the 'project' parameter or the returned chunks. Overall, marginal value added beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it performs local retrieval over KB docs, code repo docs, and Done tickets, with specific retrieval methods (BM25, embeddings, hybrid). It distinguishes itself by mentioning zero model tokens and a two-stage hybrid approach, making its purpose distinct from other tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use hybrid vs lexical mode and covers fallback scenarios. However, it does not compare directly with sibling tools like 'search_kb' nor specify when not to use this tool, leaving some ambiguity among alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

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/valentil/featureboard-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server