Dreamwork MCP Server

Official

by dreamworkhq

Overview Schema Source Related Servers Discussions Admin

TypeScript

Hybrid

List matches

list_matches

Read-only

Find and page through your ranked live job matches by filtering role, location, salary, remote, seniority, and more; use nextCursor to continue.

Instructions

Returns the account's ranked live match pool with job id, its Dreamwork page url, title, company, location, remote terms, salary, dates, match percent and saved/applied state. Filters narrow that pool; nextCursor continues a page with identical filters, and null ends the walk. A page holds 10 jobs by default and limit accepts up to 50; the next page is the previous nextCursor, which keeps the page size it was issued with. addedAfter supports overlapping discovery windows because listings can become servable after first discovery. notes describe applied filters and coverage.

Input Schema

TableJSON Schema

Name	Required	Description
`sort`	No	Order; relevance when omitted.
`bonus`	No
`limit`	No	Page size, 10 when omitted. A cursor keeps the size it was issued with.
`query`	No	Free-text search across the person's match pool.
`aiRole`	No	AI roles only.
`cursor`	No	`nextCursor` from the previous page. Send the same filters and sort, or it is refused.
`equity`	No
`function`	No	Job-function labels, comma-separated for a union, e.g. "Engineering,Product". An unknown label is refused with the list.
`industry`	No	Employer industry, e.g. "Pharma & Biotech". An unknown name is refused with the list.
`location`	No	City, region, or country; a place the gazetteer cannot resolve is refused.
`maxSalary`	No	Pay ceiling in whole annual USD.
`minSalary`	No	Pay floor in whole annual USD, e.g. 200000. Jobs with no posted pay drop out.
`seniority`	No	Seniority labels, comma-separated for a union: Junior, Mid-Level, Senior, Staff+, Director+. A hard filter: pass it when the person names a level they want only, because the stored level ranks matches but never removes other levels. It also drops roles whose level was never classified.
`addedAfter`	No	Only jobs Dreamwork first saw after this ISO date-time.
`healthcare`	No
`internship`	No	Internships, co-ops, and apprenticeships only.
`remoteOnly`	No	Shorthand for workSettings ["remote"].
`workSettings`	No	Work settings to keep, as a union; an unstated setting counts as onsite.
`minMatchPercent`	No	Lowest match percent to keep, on the 40-97 scale shown.
`postedWithinDays`	No	Employer posting date within this many days.

Output Schema

TableJSON Schema

Name	Required	Description
`jobs`	Yes
`notes`	Yes
`total`	Yes	Jobs these filters keep, across all pages. Following every nextCursor returns this many while poolChanged stays false.
`poolSize`	Yes	Jobs a walk of this pool returns before this call's filters narrow it, so it equals total when no filter is set. Dismissed and saved roles, excluded companies and same-company same-title duplicates are already left out, and so are onsite roles outside the area of someone who will not relocate, unless location or workSettings is set. query, functions and location also choose which pool is built.
`nextCursor`	Yes
`poolStatus`	Yes
`poolChanged`	Yes
`appliedFilters`	Yes
`filteredToEmpty`	Yes	True when this call's filters left none of the poolSize jobs. total 0 with this false means the pool itself is empty or still building.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 14, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnly/non-destructive/closed-world, so the bar is lower. The description adds real behavior: default page size of 10, a 50 cap, cursors preserving their issued page size, and notes describing applied filters and coverage. It stops short of stating failure modes beyond cursor/filter mismatch.

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?

Front-loads the return payload, then pagination, then edge-case rationale. Dense but mostly earns its place; nextCursor is explained twice (once for continuation, once for page-size retention), a slight redundancy.

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 return values need not be re-explained, yet the description covers pagination, filter narrowing, and notes semantics adequately for a 20-parameter list tool. Filter-interaction details (e.g. how filters combine) remain slightly thin.

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 high (85%), so the per-parameter docs already do the heavy lifting. The description adds cross-parameter semantics (cursor must reuse identical filters/sort, cursor keeps issued page size), but largely restates what limit and addedAfter already document.

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: returns the account's ranked live match pool, and enumerates returned fields (job id, company, salary, match percent, saved/applied state). The word 'live' implicitly scopes it apart from list_dismissed_matches, but no sibling is named explicitly.

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?

Explains pagination usage (nextCursor continues a page, null ends the walk) and the addedAfter overlap rationale, but gives no guidance on when to choose this over browse_listings, get_listing, or list_dismissed_matches. Usage is implied rather than stated.

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

Deploy Server