Skip to main content
Glama
Flux MCP

Flux MCP

Official
by Flux-Search

lineage

Read-only

Extract only passages from documents or web pages that answer your questions, resolving people, places, organisations and dates in context.

Instructions

Read a document or a web page and return only the passages that answer your questions, with the people, places, organisations and dates written in where a passage needs them (the name behind 'she', an exact date for 'last April'). Send text or a url, and the questions in queries. Each question is a separate pass and is billed as one. Without queries, every passage comes back, which is larger than the input. Use it to turn a long source into grounded context.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "lineage"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoA page for Flux to fetch and read instead of text. If the site refuses, you get a bad_request error and are not charged.
textNoThe document to read, up to 60000 characters. Use this or url.
queryNoOne question. Same as queries with a single entry.
queriesNoThe questions the passages should answer, up to 10. Each is a full pass and billed as one, so ask only what you need. Omit to get the whole document.
documentsNoSeveral documents in one call, each with its own text or url. Use instead of text/url. Top-level queries apply to every document unless a document has its own. Documents that cannot be read are listed and not charged.
publishedNoWhen the text was published, as an ISO date (2026-03-14). Lets relative dates such as 'last April' resolve to the right year. Not needed for a url that states its date.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety and reach profile is covered. The description adds genuinely useful behavior beyond that: each question is a separate billed pass, and query-less calls return a payload larger than the input. It says nothing about latency, ordering, or what a failed partial read looks like beyond what the schema notes.

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?

Five sentences, front-loaded with purpose and cost model, each carrying information. Slight redundancy between 'return only the passages that answer your questions' and the later restatement via queries, but no filler.

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

Completeness4/5

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

For a six-parameter, zero-required, no-output-schema tool, the description does cover what comes back (answering passages with entity/date grounding filled in) and the cost/size tradeoff of omitting queries. Error handling is delegated to the schema's url description, which is acceptable, but the description could say more about how unanswerable questions appear in the result.

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 description coverage is 100%, so the schema already carries text/url/query/queries/documents/published semantics; the description largely restates 'Send text or a url, and the questions in queries.' The one real addition is the entity-resolution rationale for published ('an exact date for last April'), which slightly deepens the schema's own explanation.

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: 'Read a document or a web page and return only the passages that answer your questions,' adding an unusual and distinguishing trait (entity/date resolution written into passages). It never names the sibling tools fetch or search, so an agent must infer the boundary rather than being told it.

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?

Gives a clear positive usage frame ('Use it to turn a long source into grounded context') and an implicit when-not: omitting queries returns everything and produces output larger than the input, which steers the agent toward supplying questions. It stops short of naming an alternative tool for plain retrieval or summarization.

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