Agency Opportunity Radar
Enables discovery of businesses via Google Places Text Search API.
Enables mobile performance measurements (LCP, INP, CLS) via PageSpeed Insights API.
Provides local SQLite database for storing profiles, audits, history, and outcomes.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Agency Opportunity Radar Find fintech websites in Argentina that need agency services."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Agency Opportunity Radar
MCP server that finds evidence-backed opportunities for digital agencies.
Agency Opportunity Radar helps an AI research public business websites, identify observable website or SEO problems, match them to an agency's declared services, and explain every score with measurements, URLs, and timestamps.
It is a research tool, not an outreach tool. It does not discover personal contact details, submit forms, send messages, or provide a standalone dashboard. The MCP client—ChatGPT, Claude, Codex, or another compatible client—remains the interface.
What the interaction looks like
Ask the connected AI:
Find fintech websites in Argentina that our agency could optimize.
The AI can first discover explicit URLs or public Google Places results, request a bounded audit for promising candidates, and then compare the saved results. A synthetic result might be summarized like this:
Río Ledger shows one directly observed technical SEO issue:
- Missing meta description (severity 3/5, confidence 0.99)
Evidence: no non-empty meta description was found on
https://rio-ledger.example/ at 2026-07-27T14:01:58Z.
Overall opportunity score: 73.5/100
- Need: 60
- Agency fit: 90
- Doability: 80
- Likely impact: 60
- Confidence: 80
Limitation: only one page was inspected. No traffic, revenue, budget, or
willingness-to-buy claim was made.The complete structured example is in
examples/example-audit-response.json.
Related MCP server: SeeYou MCP
Why this is not a lead database
A lead database answers “who might I contact?” This server focuses on a different chain of reasoning:
Need — Is there an observable problem?
Fit — Does it map to a service the agency actually offers?
Doability — Is the likely work compatible with declared capabilities and exclusions?
Evidence — Which public observation supports each finding?
The server returns those inputs and deterministic score contributions. The connected AI interprets them and keeps uncertainty visible.
Requirements
Node.js 22.19 or newer
An MCP-compatible client
No API key for manual discovery and static website audits
Optional Google Places API key for query/location discovery
Optional PageSpeed Insights API key for mobile lab measurements
Install and build
From this repository:
npm install
npm run checkThe compiled stdio server is dist/server.js. To run it directly:
node dist/server.jsThe process speaks MCP over stdio, so it normally appears idle when started in a terminal. Configure it in an MCP client instead of typing into it.
MCP client configuration
Use absolute paths for the server, database, and export directory:
{
"mcpServers": {
"agency-opportunity-radar": {
"command": "node",
"args": [
"/absolute/path/to/agency-opportunity-radar/dist/server.js"
],
"env": {
"RADAR_DATABASE_PATH": "/absolute/path/to/radar-data/opportunities.db",
"RADAR_EXPORT_ROOT": "/absolute/path/to/radar-data/exports"
}
}
}
}A copyable version is available at
examples/mcp-config.json.
Optional environment variables
Variable | Default | Purpose |
|
| Local SQLite database |
|
| Only directory to which exports may be written |
| unset | Enables Google Places Text Search discovery |
| unset | Enables mobile PageSpeed measurements |
|
| Per-request timeout |
|
| Maximum response body read |
|
| Redirect limit |
|
| Per-domain request limit |
|
| Provider and audit freshness window |
|
| Structured operational logs on stderr |
|
| Permit intentional local-site audits |
Keep RADAR_ALLOW_PRIVATE_NETWORK=0 for ordinary use. Enabling it disables the
private-network SSRF boundary and is intended only for trusted local fixtures or
development sites.
First workflow
Configure the agency with
agency_profile_set. The example atexamples/agency-profile.jsonincludes technical SEO, performance, and conversion services.Ask the AI to call
opportunity_discoverwithprovider: "manual"and a list of public websites.Call
opportunity_auditfor a returnedcandidateId.Compare two or more saved reports with
opportunity_compare.Record a human decision with
opportunity_record_outcome.Retrieve it in a later conversation with
opportunity_search_history.Export selected snapshots with
opportunity_export.
Manual discovery is intentionally useful without paid APIs:
{
"query": "fintech websites in Argentina",
"location": "Argentina",
"provider": "manual",
"websites": [
"https://public-business.example/"
],
"limit": 10
}MCP tools
Tool | Bounded job |
| Create or replace the local agency profile |
| Inspect the active profile before research |
| Normalize manual URLs or optional Places results |
| Crawl and inspect one candidate with strict limits |
| Return a compact comparison of saved snapshots |
| Filter searches, audits, and outcomes |
| Append a human-reported business outcome |
| Write selected results as JSON or CSV inside the configured root |
Supported checks
The static detector pack currently covers:
missing page titles, meta descriptions, and canonical URLs;
accidental
noindexdirectives;missing or multiple primary headings;
missing mobile viewport declarations;
multiple parser-blocking scripts;
large declared images that load eagerly;
missing static primary actions;
forms without a visible privacy link;
HTTPS pages posting forms to HTTP;
public placeholder content;
stale copyright years as low-confidence supporting evidence;
crawled internal destinations returning HTTP errors;
mobile LCP, INP, and CLS when PageSpeed is configured.
Every signal refers to one or more evidence IDs. Evidence stores the minimum necessary observation rather than full page bodies. Audit responses also include pages inspected, failed checks, next investigations, limitations, and the exact scoring configuration.
Scoring
All dimensions use a 0–100 scale. The initial, inspectable formula is:
overall =
30% need
25% agency fit
20% doability
15% likely impact
10% confidenceThis is a deterministic starting point, not an objective truth. Each audit stores its scoring version, weights, dimension values, contributing signal IDs, and plain-language reasons. A refresh creates a new snapshot instead of rewriting the old result.
Confidence falls when pages or providers fail, no inspectable page is available, or only one page is inspected. Likely impact is relative and directional; the server does not invent revenue or conversion-loss estimates.
Network and data safety
Only HTTP and HTTPS targets are accepted.
Credentials in URLs are rejected.
Loopback, private, link-local, carrier-grade NAT, multicast, reserved, and metadata-service addresses are blocked by default.
DNS is checked and pinned for each request, and every redirect is checked again.
Crawls respect
robots.txtand enforce page, redirect, response-size, timeout, concurrency, and per-domain request bounds.Login, logout, cart, checkout, and admin crawl paths are skipped.
Query tokens and common credential parameters are redacted from stored URLs.
API keys come from environment variables and are never written to results or operational logs.
Full HTML bodies are not stored.
Forms are never submitted.
CSV exports neutralize spreadsheet-formula prefixes and never overwrite files.
Exports cannot escape
RADAR_EXPORT_ROOT.The MVP collects no personal email addresses or phone numbers and performs no outreach.
Current limitations
Google Places is optional, quota-controlled, and may omit website fields.
Static HTML checks cannot prove that a visually rendered interaction works.
JavaScript-rendered content may be absent from the static response.
PageSpeed availability depends on API access and external service behavior.
The crawler inspects only a bounded subset of public pages.
It does not bypass authentication, CAPTCHAs, paywalls, or access controls.
It has no backlink index, paid-ad intelligence, social analysis, contact enrichment, CRM automation, or standalone UI.
deepincreases the bounded page sample; it does not perform the Phase 4 destructive or form-submission interactions excluded by the build plan.
Failed checks remain in the report and reduce confidence rather than disappearing.
Local storage
SQLite tables keep agency-profile snapshots, services, searches, candidates, audits, evidence, signals, scoring snapshots, outcomes, and provider cache entries. This gives a later AI conversation canonical history even when chat history is summarized or unavailable.
The server does not train an opaque ranking model from outcomes. Recorded outcomes are returned as transparent context.
Development and tests
npm run typecheck
npm test
npm run buildnpm run check runs all three.
The deterministic test suite includes:
URL normalization, secret redaction, and private-address boundaries;
redirect, timeout, and response-size handling;
ten local website fixtures spanning healthy, broken, ambiguous, and blocked behavior;
evidence-to-signal referential integrity;
score calculation and confidence penalties;
SQLite migrations, immutable snapshots, restart durability, and outcomes;
Places caching and partial PageSpeed failures;
export confinement and overwrite protection;
MCP tool discovery and end-to-end invocation over an in-memory transport.
Network-dependent live evaluations are intentionally separate. See
test/evaluation/README.md for the human-review
requirements before a public site becomes evaluation ground truth.
Project boundaries
This MVP is for evidence-led research. It is not a spam system, contact-enrichment service, automatic proposal generator, or substitute for human review. Use public and authorized data, respect site policies, and verify consequential conclusions before acting.
License
Available Tools
8 toolsagency_profile_getGet agency profileARead-onlyIdempotent
Returns the current local agency profile so assumptions can be checked before research.
Inputs: no named parameters. Returns: result
agency_profile_setSet agency profileBDestructive
Creates or replaces the local agency profile used for fit and doability scoring.
Inputs: name (required), services (required), notes, targetMarkets, +3 more. Returns: result
opportunity_auditAudit a public website opportunityB
Runs a bounded, robots-aware public website audit and returns observations, evidence-linked signals, explicit failures, and deterministic score reasons. It never submits forms.
Inputs: url, depth, refresh, maxPages, +2 more. Returns: result
opportunity_compareCompare audited opportunitiesCRead-onlyIdempotent
Returns a compact, consistently shaped comparison of saved audit snapshots without generating sales copy.
Inputs: opportunityIds (required), serviceIds. Returns: result
opportunity_discoverDiscover opportunity candidatesA
Finds and normalizes public business websites using explicit URLs or the optional Google Places provider. It does not deeply audit them.
Inputs: query (required), limit, location, provider, +2 more. Returns: result
opportunity_exportExport opportunitiesA
Writes selected saved opportunities as JSON or CSV inside the configured export directory. Existing files are never overwritten.
Inputs: format (required), opportunityIds (required), filename. Returns: result
opportunity_record_outcomeRecord opportunity outcomeA
Appends a human-reported outcome to an audited opportunity. It does not contact the business or change any external system.
Inputs: status (required), opportunityId (required), notes, value, +2 more. Returns: result
opportunity_search_historySearch opportunity historyCRead-onlyIdempotent
Retrieves persisted searches, audit snapshots, and outcomes using transparent filters.
Inputs: to, from, limit, query, +3 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool has a clear, distinct purpose without overlap. Profile tools manage the agency profile, opportunity discovery and audit are separated, and post-audit tools (compare, history, outcome, export) serve unique functions.
All tools follow a consistent 'domain_action' pattern using snake_case, with 'agency_profile_' or 'opportunity_' prefixes and clear verbs (set, get, discover, audit, compare, search_history, record_outcome, export).
8 tools align well with the server's purpose. Each tool covers a necessary step in the workflow from profile setup to discovery, audit, comparison, history, outcome recording, and export without being excessive or insufficient.
The tool set covers the main workflow comprehensively, but lacks explicit update/delete tools for audits or opportunities. There is also no direct listing of all opportunities, though search_history with filters partially addresses this.
Maintenance
Related MCP Connectors
SEO rankings, search performance, keyword opportunities, competitors and site audits.
Public-site SEO/AEO readiness scans with evidence scores, issues, and clear measurement scope.
Site scores, audits, Search Console, keywords, competitors, authority and AI visibility tools.
SEO for agencies: rank tracking, site audits, Search Console, GA4, backlinks and AI visibility.
Related MCP Servers
- FlicenseAqualityBmaintenanceEnables comprehensive website SEO analysis including crawling, on-page audits, site structure visualization, and content topic classification with taxonomy mapping.71-
- AlicenseNot gradedqualityBmaintenanceEnables SEO auditing of websites from MCP-capable IDEs, providing crawler and rendered views, scoring, and ROI-ranked fix plans that agents can apply directly in the repository.MIT
- AlicenseAqualityCmaintenanceEnables auditing a site for SEO and AI-engine visibility, working the queue of measured problems, and checking whether fixes moved rankings or citations.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables agents to research competitors, keywords, ads, and AI citations, and to audit public websites for SEO, AEO, and GEO readiness with prioritized fixes.MIT