Partner and Member Directory Extractor MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| APIFY_TOKEN | Yes | Your Apify API token from console.apify.com/account/integrations. The server lists its tool without a token; a call needs one. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| extract_directory_companiesA | Turn a vendor partner directory or a trade body member list into one company row per listing. Give directory_url or directory_urls (up to 20). Reads directories built on PartnerPage (for example https://www.clay.com/en/experts or the Zapier partner directory) through PartnerPage's public listing API, the Shopify Partner Directory (any https://www.shopify.com/partners/directory/... page), and member lists that link to one profile page per member. Each row: listing_name, company_domain, website, listing_url, tier, tags, location, rating, review_count, partner_since, and the email and phone the directory itself publishes. robots.txt is checked before every request. A directory that cannot be read (it builds its list in the browser) returns one free row with row_status unsupported. A run that does not succeed is returned as an error with its run ID. Read-only; requires an APIFY_TOKEN; Apify charges per company row. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of selecting the wrong one. Its description signals a single, well-bounded operation (directory → company rows) with no sibling tools to confuse it with.
The lone name, extract_directory_companies, follows a clear verb_noun_plural pattern in snake_case. There are no competing conventions to clash with, and the name is self-describing.
A one-tool surface is thin even for a single-purpose extractor: there is no companion for checking run status, fetching a prior run's rows, or listing supported directory types, which the description implies are real concerns (run IDs, errors, per-row billing). It is defensible but borderline.
The async lifecycle is a dead end — the description says failed runs return a run ID, yet there is no tool to poll, retry, or retrieve results for that run, and no way to discover which directories are supported. The single extraction call itself is thorough, but agents will hit a wall after submitting work.