Forage MCP: The Knowledge Layer Your Agent Is Missing
Riccardo Minniti / Ernesta Labs · [email protected] · useforage.xyz
Your agent hallucinates. Let's be honest about that.
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."
You're not running an intelligent agent. You're running a smart model with amnesia.
Every research workflow starts from zero. Your agent searches, reads, answers, forgets. Tomorrow, when you ask about the same company, the same market, the same competitors—it learned nothing. Zero institutional knowledge. Zero compounding research.
Meanwhile, your competitor's agent? It's built a knowledge graph of 1 million entities. When it researches Stripe, it already knows the investors, the hires, the tech stack, the acquisition history. It adds what's new and moves on. Six months in, their agent knows your market better than you do.
What does it cost you when your agent is starting from zero every single time, while smarter agents are building permanent intelligence?
What if your agent actually had a memory?
Imagine your agent researched Stripe six weeks ago. Found funding, competitors, tech stack, hiring timeline, key executives. Today you ask about Stripe again. Your agent says: "I already know Stripe. Last time I found 15 competitors, Series D at $95B valuation, currently hiring 30 engineers on the infrastructure team. Here's what changed since then." No re-scraping. No hallucinations. Just: this is what we know, here's what's new.
That's not a research tool. That's an intelligence asset.
What would actually be different if your agent could:
- Run market analysis on Day 1 and still reference it on Day 180, watching hiring patterns, funding announcements, feature launches in real-time
- Answer "find me leads matching X criteria" and check its graph first—return cached results instantly, add new matches, never double-scrape
- Tell you "Company A and Company B share three investors" not from guessing, but from a 1-million-entity graph it built over months
- Track a prospect's hiring signals over time and tell you "they're moving from product to sales focus—here's when they'll be buying"
- Run causal analysis on market shocks and tell you which of your prospects will be affected and why
Step into that version of your workflow for a second. Every research compounds. Every discovery sticks. Your agent gets smarter, faster, cheaper every single day.
What does your competitive position look like then? What decisions become obvious that aren't obvious now?
The Knowledge Graph: What Compounds
Every tool call feeds a persistent knowledge graph. Your agent's research accumulates across sessions. The more it uses Forage, the smarter it gets.
Not a cache. Not a log. A structured graph with nearly 1 million entities and growing: companies, people, domains, funding rounds, competitors, technologies, markets, legal entities, geopolitical events, financial instruments. A FIBO-aligned ontology with 150+ entity types and 200+ relationship types including causal chains, contagion pathways, regime transitions, and shock propagation.
When your agent needs to know something, it checks the graph first. What it already knows, it doesn't re-learn. What is new, it adds. What is connected, it discovers.
This is the differentiator. Other tools give your agent a response. Forage gives your agent a memory that never forgets and a reasoning layer that connects everything it has ever learned.
36 Tools. One Connection.
Core Tools
Skills: Multi-Source Intelligence Bundles
One call. Five to eight sources merged into a single intelligence package.
Graph Tools
Who This Is For
AI agents running live research workflows:
- Sales development teams using agents to find and qualify leads
- Competitive intelligence analysts building market maps on demand
- Investment research workflows discovering funding rounds and cap table changes
- Recruitment pipelines finding decision-makers and their hiring signals
- Compliance systems tracking entity relationships and regime changes
Anyone whose agent makes decisions based on data: If your agent needs to know something real about the world—not guess, not hallucinate, but know—and remember what it learned so next time it's smarter, this is for you.
What Changes
Before Forage: Agent searches → reads results → answers → forgets. Repeat tomorrow.
With Forage: Agent searches → graph stores it → tomorrow agent knows it → adds what's new → moves on. Knowledge compounds.
Real scenario: You ask your agent about Stripe's competitors. With Forage, your agent profiles 15 competitors in 2 minutes, sources funding for each, finds key execs, detects which ones are hiring aggressively right now. You get a decision-ready landscape. Next month you ask again—your agent still has all 15 profiles, adds the hiring changes, the new funding rounds. You're not starting from zero.
That knowledge advantage grows every day.
And on the flip side: what happens if you don't?
Two days from now: you're asking your agent the same questions about the same companies because it forgot everything.
Two weeks from now: you've spent hours re-scraping data you already scraped once. Your competitor's agent has added 200 new entities to its graph.
Two months from now: you're still paying for email lookups you already did. You're still hallucinating on company facts. Your lead generation is still manual. Your agent still has no memory.
Two years from now: your agent is exactly where it was two years ago. Zero institutional knowledge. Zero compounding intelligence. Zero advantage. Your competitor's agent? It's analyzed 10,000 companies. It knows hiring signals before they're public. It sees the connections you can't. It's profitable because it remembers.
That's the cost of amnesia. Not in dollars. In momentum. In decision quality. In how far behind you fall.
Meanwhile the agents that connected to Forage six months ago? They know more about their markets than the humans do. Because everything they've ever found is still there. Connected. Growing. Compounding every single day.
What This Is. What It Isn't.
This is a knowledge layer for AI agents: web intelligence plus persistent memory. One connection, 36 tools, a graph that never forgets.
This is not a search wrapper. Not a RAG system. Not a vector database. Not a chatbot with browsing.
This is pay-per-call. Your agent uses it, you see the cost. Forage gives every new user $5 in free credits, on top of anything Apify offers.
This is not a subscription. No monthly fee. No minimum commitment.
Your First $5 Is on Forage
$5 in free credits, loaded to your account the moment you connect. This is Forage's own credit, on top of anything Apify gives you as a platform user. New to Apify or a power user, the $5 starts the same way.
Real cost models:
- Sales team using Forage daily to prospect: $300-600/month (for a human researcher: $5-10k/month salary)
- Due diligence pipeline running market scans: $200-400/month in data costs (vs. $2k/month Clearbit + S&P Capital IQ subscriptions)
- Competitive intelligence in-house: $100-200/month (vs. $1k/month third-party intelligence services)
You pay for what your agent uses. Scale up or down instantly. No vendor lock-in.
How It Works
When your agent uses Forage, it makes a single MCP connection. Your request routes to our server, which orchestrates multiple Apify data actors in parallel—web scrapers, email finders, LinkedIn extractors, market crawlers. Each actor runs simultaneously. Results merge, deduplicate, and enrich into a single response. The entire result feeds into a persistent knowledge graph. Next time you ask about the same company or market, your agent already knows.
No API keys to manage. No rate limits to chase. No integration tax. You send Apify credentials once and Forage handles the rest: data sourcing, deduplication, graph enrichment, causal analysis.
Setup: 30 Seconds, One Token
Get an Apify token at console.apify.com. That's it. No additional API keys needed.
Forage adds $5 in free credits to your first session, regardless of your Apify account status. You're live.
Claude Desktop (add to %APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"forage": {
"command": "npx",
"args": ["-y", "@anthropic/mcp-proxy", "https://ernesta-labs--forage.apify.actor/mcp"],
"env": { "APIFY_API_TOKEN": "YOUR_APIFY_TOKEN" }
}
}
}
Cursor / Windsurf:
{
"mcpServers": {
"forage": {
"command": "npx",
"args": ["-y", "@anthropic/mcp-proxy", "https://ernesta-labs--forage.apify.actor/mcp"],
"env": { "APIFY_API_TOKEN": "YOUR_APIFY_TOKEN" }
}
}
}
Docker:
{
"mcpServers": {
"forage": {
"command": "docker",
"args": ["run", "--rm", "-i", "-e", "APIFY_API_TOKEN", "ghcr.io/ernestalabs/web-intelligence-mcp:latest"],
"env": { "APIFY_API_TOKEN": "YOUR_APIFY_TOKEN" }
}
}
}
n8n / LangGraph / Custom: Connect to https://ernesta-labs--forage.apify.actor/mcp with your Apify token in the Authorization header.
No API Keys. No Setup.
You don't configure SerpAPI, Jina, Google Places, Apollo, or any other service. That's our problem. You bring Apify credentials. We handle everything else: sourcing, orchestration, deduplication, graph enrichment, causal analysis. One token. Full stack.
FAQ
Q: Is this a search wrapper? No. Search is one capability. We search, scrape, discover emails, extract LinkedIn data, pull Crunchbase, check reviews, map markets, analyze competitors, detect hiring signals, and synthesize it all into a knowledge graph that remembers. Every result feeds the graph. Every query checks the graph first.
Q: Do I need multiple API keys? No. One Apify token. We orchestrate everything server-side.
Q: How fresh is the data? Real-time for web searches and scrapes. Graph data is what your agent discovered, plus what others using Forage have discovered and shared into the graph. You own your queries; the graph is shared intelligence.
Q: Can I use this offline? No. Forage is a web service. Your agent connects via MCP to live data sources. Every query hits the web.
Q: What about rate limits? You share Apify infrastructure. Each actor has its own rate limits, but we parallelize: if one scraper hits a limit, five others finish while we wait. Your results still come back fast.
Q: Does the knowledge graph persist? Yes. Everything your agent discovers stays in the graph. You can query it, add claims to it, analyze causal chains, simulate interventions. Your agent's institutional knowledge grows every session.
Q: How do I stop costs? Stop calling. That's it. No subscriptions, no minimums. $0 spend = $0 bill. You control every call.
Q: What if your service goes down? Your agent keeps working on cached graph data. It just can't do live research. You'll hear from us immediately if there's an outage.
Contact
- Email: [email protected]
- Website: useforage.xyz
- GitHub: github.com/ErnestaLabs/web-intelligence-mcp
- Apify: apify.com/ernesta_labs/forage
MIT License. Copyright (c) 2026 Riccardo Minniti / Ernesta Labs