Zearch MCP

Official

Overview Schema Source Related Servers Discussions Admin

Research with checked answers

research

Answer questions with cited web evidence: search or read a page, draft only from selected passages, and verify each paragraph against its source before returning the result.

Instructions

Ask Zearch a question. Zearch searches the web (or reads the page or site you give it), Jev selects the passages that answer it, a writer drafts from those passages only, and Jev checks every paragraph against its cited source before the answer is returned. Unsupported paragraphs are cut; if nothing survives you get the selected source passage (answer_type "excerpt").

Modes and credits: standard (1, a direct answer in seconds), deep (5, a cited report from up to 8 sources), compare (2, a side-by-side comparison), scrape (1, what one public HTTPS page says; needs url), crawl (3, up to five pages of one site; needs url), reverse (10, static analysis of how an app, repo or site works; needs url, runs on a queue and can take minutes). A follow-up with parent_id that needs no new search costs 0.3. Errors are free.

Returns the answer as Markdown with [n] citations, the sources with the exact excerpt Jev read, per-paragraph support scores, and suggested follow-ups.

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": {
      "query": "<query>"
    },
    "name": "research"
  }
}

Input Schema

Name	Required	Description	Default
`url`	No	Public HTTPS URL. Required for scrape, crawl and reverse; ignored otherwise.
`mode`	No	How much research to do. See the tool description for costs.	standard
`query`	Yes	The question, in plain language.
`parent_id`	No	Id of a previous run, to ask a follow-up in the same conversation.
`use_notes`	No	Also use the account's private Zearch notes and documents as evidence.

Output Schema

Name	Required	Description
`id`	Yes
`mode`	No
`error`	No
`query`	No
`answer`	No	Markdown with [n] citations.
`object`	No
`status`	Yes	pending, streaming, complete, error, interrupted or redacted.
`created`	No
`sources`	No
`updated`	No
`followups`	No
`parent_id`	No
`timing_ms`	No
`answer_type`	No	verified: every paragraph passed Jev. excerpt: the selected source passage, because no draft could be supported.
`verification`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 12, 2026

TDQS

A4.2/5.0

Behavior3/5

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

Adds real behavior beyond the annotations: per-mode credit costs, error-free billing, the paragraph-censoring rule ('unsupported paragraphs are cut' with an 'excerpt' fallback), and queue latency for reverse. Against that, the annotations declare readOnlyHint=false and idempotentHint=false without the description explaining what state a call creates or whether a retried call is billed twice, leaving a small ambiguity.

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

Conciseness5/5

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

Front-loads the core action and the trust guarantee, then moves to a dense mode/credit list that reads as a lookup table rather than prose. No sentence is filler and the return-format line is deferred to the end where it belongs.

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?

An output schema exists, so the brief return summary is more than sufficient, and the mode list fully covers the 5-parameter surface. The only missing piece is operational: for reverse (queued, minutes-long) the agent is not told how to retrieve or poll a result, which matters for a non-idempotent, credit-charging call.

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?

With schema coverage at 100% the schema already explains all five fields, yet the description still adds value by mapping url to the three modes that need it ('ignored otherwise') and pricing parent_id follow-ups at 0.3 credits. It never mentions use_notes, so one parameter's effect on behavior is left entirely to 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?

Opens with a concrete verb and resource ('Ask Zearch a question') and then names the full pipeline, so the agent knows exactly what happens between input and answer. The modes paragraph enumerates six distinct behaviors (standard, deep, compare, scrape, crawl, reverse), which separates it cleanly from the sibling run/account 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?

Gives strong mode-selection guidance: cost per mode, which modes require url, and which modes are slow/queued ('reverse... runs on a queue and can take minutes'), plus the parent_id follow-up discount and free errors. It stops short of naming alternatives for recovering a queued result (e.g. get_run/list_runs), which is the one routing gap.

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

Deploy Server