Skip to main content
Glama
Sign In
Kilonova MCP

Kilonova MCP

by MilnaOS
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

kb_search

Search a Kilonova knowledge base for records matching a natural-language query, including session notes, decisions, project state, or domain-specific topics.

Instructions

Search a Kilonova knowledge base for records matching a query. Pass topic="claude_context" to search your session notes, decisions, and project state. Pass any other topic name for domain-specific KBs (game systems, research, codebases, etc.).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "topic": "<topic>",
      "query": "<query>"
    },
    "name": "kb_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesNatural language search query
topicYesKB topic to search (e.g. "claude_context", "my_project")
entity_typesNoOptional: filter to specific entity types

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A3.5/5.0
Behavior3/5

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

No annotations are provided, so the description carries the burden. 'Search' implies a non-destructive read, which is a safe inference, but nothing is said about result ranking, caps/limits, or what happens when the topic doesn't exist — meaningful gaps for a tool with zero annotation coverage.

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?

Three short sentences, front-loaded with the core action, then the topic semantics. Every sentence carries information; no boilerplate or repetition.

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?

For a search tool with no output schema, the description never says what a result looks like (raw records, snippets, relevance scores) or whether results are truncated, and `entity_types` is left entirely to the schema. Adequate but with clear gaps.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3. The description earns the extra point by giving real semantics for `topic` — the special "claude_context" value maps to session notes, decisions, and project state, and any other name maps to a domain KB — which the schema only hints at with examples.

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

Purpose4/5

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

States a specific verb and resource: 'Search a Kilonova knowledge base for records matching a query.' It doesn't explicitly distinguish itself from siblings like kb_load or kb_topics, but the search-vs-load framing is inferable.

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

Usage Guidelines3/5

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

It gives concrete guidance on which topic value to pass ("claude_context" for session notes vs. other topic names for domain KBs), which is real usage guidance for the required parameter. It never says when to use kb_search instead of kb_load, kb_topics, or dot_load, so tool selection among siblings is left to inference.

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

Deploy Server

Other Tools