Early AccessEvery agent is free to connect — no card, no checkout. Paid agents are coming.
Filter by Industry (who it's for) and Discipline (what it does). Pick either, or both.
Every agent is scanned and human-reviewed, and your API keys are only sent to the hosts it declares.How it works
FindAgent is a cross-LLM marketplace of focused AI agents. You find an agent, connect it to the AI app you already use — Claude, ChatGPT, Gemini, Cursor, the FindAgent CLI, or any MCP client — and use it where you already work.
Browse across two axes: the Industry an agent serves (who it is for) and the Discipline it embodies (what it does). Pick either or both, then refine by item type, tags, and integrations, or search for what you need.
Open an agent and follow its steps: install it locally with the FindAgent CLI, or, for a hosted agent, add its MCP server URL as a connector to wire it into Claude, ChatGPT, Gemini, Cursor, or any MCP client.
Every agent is scanned and human-reviewed before it is published, and your API keys are only sent to the hosts an agent declares. Declarative agents ship no executable code.
Every industry and discipline
Turns your domain research into a sourced brief — and flags any claim without a source as critical.
Monte Carlo sprint velocity forecasting with P50/P80/P95 delivery dates
Turns read-only BigQuery metric results into deterministic deltas/trends + narrative
Square POS Menu Engineering analysis with discount/promotion/removal recommendations
Pools feedback from four systems, themes it, and ranks by affected ARR — not by who complained loudest.
Automated weekly Stripe MRR/churn/NRR report with anomaly detection, posted to Slack
Extracts hardcoded strings into translation keys, builds locale files, and flags RTL overflow risk.
Summarizes Looker/BI dashboards into deterministic KPIs, highlights and recommendations
Correlates Datadog metric anomalies with logs into a structured RCA, posted to Slack/PagerDuty
Scores competitor moves across pricing, product, hiring, reviews and changelog into a weekly digest.
Weekly diff of competitor ads, pricing, SERP and messaging — and it always tells you what it could not see.
Monitors Twilio SMS delivery rates with Datadog metrics and Slack root-cause alerts
Scores a suspicious email 0–100 with the header, URL and language evidence — never fetching a single link.
Designs the whole drip series — trigger, cadence, A/B subjects, exit rules — as a draft it can never send.
Scores your site for AI-search visibility and writes the robots.txt, llms.txt and JSON-LD to fix it.
Classifies workplace incidents under OSHA 29 CFR 1904 with Notion + Slack alerts
Scores every property listing 0–100 for completeness and returns a prioritised fix list. Read-only.
Says what your own material supports — and refuses to write the rest
GA4 + HubSpot buyer-intent lead scoring with hot-lead Slack digests for real estate
Reconciles Salesforce pipeline forecasts with historical win rates for adjusted projections
Scores GEO compliance against a versioned ruleset and builds the fix PR — schema.org, llms.txt, canonicals.
Reports channel economics and retention without inventing what a customer is worth
Groups, de-noises and priority-scores your SIEM alerts, then writes the analyst read. GET-only, always.
Finds the duplicates, bad formats and missing fields in your CRM records — as proposals it can never apply.
Finds the exact step killing your activation rate and returns three ranked A/B tests to fix it.
Syncs LinkedIn Recruiter InMails with Greenhouse ATS, reports to Notion and Slack
Extracts, three-way matches, codes and VAT-checks an invoice batch into draft ERP records for approval.
Runs your beta from candidate selection to a GA-readiness score — and never emails a customer itself.
Finds the reports nobody opens — and the ones everyone opens that quietly broke.
Assesses applications requirement by requirement — reasoning first, and never an automatic rejection.
Asks the assistants your buyers ask, and reports what they say about you.
Reviews a PR against your repo's own conventions, and stays quiet when there's nothing to say.
Blank page to a complete PRD, or an existing PRD to a list of what it's missing.
A job description that describes the job, and an interview kit that tests what it asks for.
Decides where every ticket goes — the right group, an engineering issue, or a product theme.
Puts the pricing clause and the actual arithmetic in front of whoever is about to approve.