Skip to main content
Glama
mambalabsdev

Company Discovery List Builder MCP Server

by mambalabsdev

Build Company List

build_company_list
Read-onlyIdempotent

Build targeted company lists by market definition: find companies currently hiring for specific roles from live job boards, or US public companies mentioning your phrase in SEC filings.

Instructions

Build a list of companies from a market definition, in two modes. hiring returns companies currently advertising for your role keywords, built from a live index of public Greenhouse and Ashby job boards; role_keywords are matched as whole words against live job titles, so account executive matches Enterprise Account Executive and does not match Executive Assistant. filings returns US public companies whose SEC filings of the form types you name contain your exact phrase. location_contains is a plain substring test against the job board's own free text location string, so Remote does not match US Remote. min_open_jobs is a rough size proxy. resolve_domains looks up each company's website, which adds roughly a second per company and resolves about two thirds of the time, so check domain_status and domain_confidence before trusting a domain. The underlying company universe is rebuilt about monthly on its own; refresh_universe forces a fresh enumeration and is rarely what you want. You are billed per company returned, not per company examined, so max_companies is the cost dial. Requires an APIFY_TOKEN and consumes Apify credits. Read only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeYeshiring returns companies currently hiring for your role keywords, built from a live index of public Greenhouse and Ashby job boards. filings returns US SEC filers whose filings contain your phrase.
filing_formsNoComma separated SEC form types, for example 10-K,10-Q. Used in filings mode. Default: "10-K".
filing_phraseNoExact phrase searched in SEC filings, for example agentic AI. Used in filings mode.
max_companiesNoHow many companies to return, 1 to 2000. Sent as a string so it works from Clay. You are billed per company returned, not per company examined. Default: "100".
min_open_jobsNoSkip companies with fewer open roles than this. A rough size proxy. Sent as a string so it works from Clay. Default: "1".
role_keywordsNoComma separated. Matched as whole words against live job titles, so account executive matches Enterprise Account Executive and does not match Executive Assistant. Leave empty to match any role. Used in hiring mode.
resolve_domainsNoLook up each company's website. Off by default: it adds roughly a second per company and about two thirds of companies resolve. Check domain_status and domain_confidence before trusting a result. Default: true.
refresh_universeNoForce a fresh Common Crawl enumeration instead of the cached one. The cached universe is rebuilt about monthly on its own, so leave this off unless you need the newest crawl. Default: false.
location_containsNoSubstring match against the job location string, for example London, Remote, New York. Locations are free text on every job board, so this is a plain substring test: Remote does not match US Remote.
Behavior5/5

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

Beyond annotations (readOnly, openWorld, idempotent, non-destructive), the description discloses latency and success rates for resolve_domains, matching behavior (whole-word vs substring), the monthly universe rebuild, per-company billing, and the need to check domain_status/domain_confidence. This is extensive and adds significant value without contradicting annotations.

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 a dense single paragraph but is front-loaded with the core purpose and each sentence provides useful detail. However, it could be more scannable with bullet points or short sections given its length, earning a 4 rather than 5.

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?

There is no output schema, so the description carries the burden of explaining return values. It mentions domain_status and domain_confidence, but does not outline the overall result structure (e.g., company fields). For such a configurable tool, this is a notable gap, though the core use cases and side effects are well documented.

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

Parameters5/5

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

Although the schema already covers all parameters (100% coverage), the description enriches several: role_keywords gets concrete examples of whole-word matching, location_contains explains the substring test with a counterexample, resolve_domains notes time and success rate, and max_companies is framed as a cost dial. This exceeds the baseline 3 for high schema coverage.

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 opens with 'Build a list of companies from a market definition, in two modes,' which clearly states the verb, resource, and scope. It explicitly names the two modes (hiring, filings) and details what each returns, effectively distinguishing the tool's behavior without needing sibling comparisons.

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

Usage Guidelines5/5

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

It provides concrete guidance on when to use each mode: hiring for live job boards, filings for SEC filings. It also warns against using refresh_universe ('rarely what you want'), explains billing implications of max_companies, and notes token/credit requirements—clear context for usage and parameter selection.

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/mambalabsdev/mcp-company-discovery-list-builder'

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