Forage — Web Intelligence & Knowledge Graph MCP Server

Web intelligence, verified B2B contacts, and a persistent knowledge graph for AI agents.

Local serverstdio

What is the Forage — Web Intelligence & Knowledge Graph MCP server?

If you already use Forage — Web Intelligence & Knowledge Graph, the forage — web intelligence & knowledge graph mcp server is the piece that lets your assistant work with it directly. Web intelligence, verified B2B contacts, and a persistent knowledge graph for AI agents.

What the server does

You ask it: "Who are Stripe's main competitors?" It tells you confidently about companies that don't exist. You ask: "Find me 50 qualified leads." It returns hallucinations with made-up email addresses. You say: "What did you learn about this market last month?" It says: "I have no memory of last month."

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • search_web — Search the web, get real results
  • scrape_page — Extract clean text from any URL
  • get_company_info — Domain to full company profile with contacts
  • find_emails — Discover verified B2B emails with confidence scores
  • find_local_leads — Find local businesses by type and location
  • find_leads — Generate B2B lead lists filtered by title/location/industry
  • list_verified_actors — Browse available data source actors
  • get_actor_schema — Get input schema for any actor
  • call_actor — Run any data actor with custom input
  • search_apify_store — Search 1500+ data actors
  • query_knowledge — Search the graph for previously discovered entities
  • enrich_entity — Full profile with all relationships from the graph

Installation

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Credentials and setup notes

Configuration is passed through the environment: APIFY_API_TOKEN, YOUR_APIFY_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Where it fits

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Forage — Web Intelligence & Knowledge Graph's toolset — search_web, scrape_page, get_company_info and 11 more — is a fair guide to whether it matches your workflow. It is maintained by ErnestaLabs; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Forage — Web Intelligence & Knowledge Graph.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
search_webSearch the web, get real results
scrape_pageExtract clean text from any URL
get_company_infoDomain to full company profile with contacts
find_emailsDiscover verified B2B emails with confidence scores
find_local_leadsFind local businesses by type and location
find_leadsGenerate B2B lead lists filtered by title/location/industry
list_verified_actorsBrowse available data source actors
get_actor_schemaGet input schema for any actor
call_actorRun any data actor with custom input
search_apify_storeSearch 1500+ data actors
query_knowledgeSearch the graph for previously discovered entities
enrich_entityFull profile with all relationships from the graph
find_connectionsFind relationship paths between any two entities
add_claimStore a sourced assertion with confidence score

How to install the Forage — Web Intelligence & Knowledge Graph MCP server

{
  "mcpServers": {
    "forage": {
      "command": "npx",
      "args": ["-y", "@anthropic/mcp-proxy", "https://ernesta-labs--forage.apify.actor/mcp"],
      "env": { "APIFY_API_TOKEN": "YOUR_APIFY_TOKEN" }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
APIFY_API_TOKENCredential the server authenticates with.Yes
YOUR_APIFY_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Forage — Web Intelligence & Knowledge Graph to search web.
  • Use Forage — Web Intelligence & Knowledge Graph to scrape page.
  • Use Forage — Web Intelligence & Knowledge Graph to get company info.

Frequently asked questions

It connects Forage — Web Intelligence & Knowledge Graph to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (search_web, scrape_page, get_company_info, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Forage — Web Intelligence & Knowledge Graph directly.