Competitive change evidence

Know what changed before your customers do.

Know when competitor prices and plan names change. Keep before-and-after evidence for your next pricing decision, sales conversation, or client report.

✓ No card or sales call ✓ Persistent daily checks ✓ Upgrade the same workspace

Preview a live monitor now

See the prices and plans we can detect on a public pricing page, then keep watching it with a free monitor.

Let the agent prove recurring value first

Connect the remote MCP server and ask the agent to capture a free source baseline. The tool tells the agent what was observed, how often to check it, and when persistent monitoring is worth activating.

1. Add the remote MCP server

Free preflight checks work without an API key.

{ "mcpServers": { "ground-truth": { "url": "https://ground-truth-mcp.anishdasmail.workers.dev/mcp" } } }

2. Ask the agent to preview monitoring

No checkout or API key is needed for the baseline.

Use preview_monitor with target_type=pricing_page and target_value=https://stripe.com/pricing. Show me the baseline and recommended schedule. Do not recommend checkout unless the preview succeeds.

Example input

The client should call this tool with this argument.

{ "name": "preview_monitor", "arguments": { "target_type": "pricing_page", "target_value": "https://stripe.com/pricing" } }

Example output shape

Response evidence varies by run.

{ "status": "baseline_ready", "recommended_schedule": "daily", "persistence": "preview_only", "upgrade_tool": "create_monitor" }

The preflight workflow

Ground Truth sits between an agent’s discovery step and its decision to trust or act.

1. Discover

The agent finds an external URL, API endpoint, or claim.

2. Check

Ground Truth fetches the resource and inspects observable response and header signals.

3. Decide

The agent receives PASS, WARN, or FAIL with structured evidence.

4. Proceed or stop

The agent continues, asks for caution, or stops before relying on the resource.

Three checks drive the product

Start with the checks agents already use most: endpoint behavior, HTTP security configuration, and evidence for claims.

Preflight an endpoint or API

Check whether an unfamiliar resource responds, what status and content type it returns, whether it redirects, and whether auth or rate limits are blocking it.

check_endpoint

Inspect security headers

See which common browser-facing headers are present or missing. The result is a configuration signal, not a vulnerability scan.

inspect_security_headers

Verify an external claim

Check supplied evidence URLs for the keywords you specify before an agent repeats a pricing, policy, support, or compliance claim.

verify_claim

Combine the preflight

Run endpoint and header checks together and give the agent one decision-oriented result with both evidence sets.

preflight_endpoint

Why preflight matters

An external resource can exist and still be the wrong thing to trust. Preflight makes the observable uncertainty explicit before the agent acts.

Availability changes

An endpoint can move, redirect, require credentials, rate-limit, or fail after an agent has discovered it.

Headers reveal configuration signals

Missing HSTS, CSP, or framing controls should be visible to the agent before it makes a browser-facing recommendation.

Claims need direct evidence

Keyword support on supplied public sources helps an agent show what it checked without pretending that silence proves a claim false.

Evidence should drive the next step

PASS means continue, WARN means inspect the evidence, and FAIL means stop or ask for a different resource.

Put the check before the action

The agent should call the relevant tool as soon as it discovers an unfamiliar resource, not after it has already trusted the result.

API discovery

Agent finds https://api.example.com/v1/users and calls preflight_endpoint before using it.

Security signal

inspect_security_headers reports HTTPS and the headers it can observe, including missing recommendations.

Evidence check

verify_claim checks supplied policy or pricing pages for explicit supporting keywords.

Decision

The agent uses PASS, WARN, or FAIL to proceed, pause for review, or stop.

Start with a real watchlist

Create three persistent monitors before paying. Upgrade self-serve when your team needs hourly checks, more sources, or higher run volume.

Free

Competitive watchlist

$0

Three real monitors with daily or weekly evidence checks.

  • 3 persistent monitors
  • Evidence history and change reports
  • Webhook alerts and share links
  • check_endpoint
  • inspect_security_headers
  • preflight_endpoint
  • verify_claim (5 calls/month)
  • 100 monitor actions/month
  • No card or signup form
Paid

Persistent monitoring

From $9/month

For agents that need authoritative sources kept fresh automatically. Three tiers — 10, 40, or 150 active monitors.

  • Single Stripe card subscription
  • Hourly, daily, or weekly schedules
  • Includes paid-gated verification tools
  • Saved monitors with evidence history
  • Change reports for teams and agents
  • Read-only share links for evidence
Agentic path: Agents can call preview_monitor first, then create a persistent monitor with a free watch key. Paid plans add hourly schedules, more sources, and larger quotas; x402 remains available for autonomous one-off research. Open the watch dashboard →

API examples

Use Ground Truth directly over HTTP if you want the free first check in a script, backend, or agent loop.

Direct API curl call

Initialize the MCP session, then call the free endpoint check with no API key.

SESSION_ID="$(curl -i -s -X POST https://ground-truth-mcp.anishdasmail.workers.dev/mcp \ -H "Accept: application/json, text/event-stream" \ -H "Content-Type: application/json" \ -d '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"ground-truth-example","version":"1.0.0"}},"id":0}' | tr -d '\r' | awk '/^mcp-session-id:/ {print $2}')" curl -X POST https://ground-truth-mcp.anishdasmail.workers.dev/mcp \ -H "Accept: application/json, text/event-stream" \ -H "Content-Type: application/json" \ -H "Mcp-Session-Id: $SESSION_ID" \ -d '{ "jsonrpc": "2.0", "method": "tools/call", "params": { "name": "check_endpoint", "arguments": { "url": "https://example.com" } }, "id": 1 }'

JavaScript fetch example

Run the same no-key endpoint check from code.

const initResponse = await fetch("https://ground-truth-mcp.anishdasmail.workers.dev/mcp", { method: "POST", headers: { "Accept": "application/json, text/event-stream", "Content-Type": "application/json", }, body: JSON.stringify({ jsonrpc: "2.0", method: "initialize", params: { protocolVersion: "2025-03-26", capabilities: {}, clientInfo: { name: "ground-truth-example", version: "1.0.0", }, }, id: 0, }), }); const sessionId = initResponse.headers.get("mcp-session-id"); if (!sessionId) { throw new Error("Missing mcp-session-id from initialize response"); } const response = await fetch("https://ground-truth-mcp.anishdasmail.workers.dev/mcp", { method: "POST", headers: { "Accept": "application/json, text/event-stream", "Content-Type": "application/json", "Mcp-Session-Id": sessionId, }, body: JSON.stringify({ jsonrpc: "2.0", method: "tools/call", params: { name: "check_endpoint", arguments: { url: "https://example.com", }, }, id: 1, }), }); const result = await response.json(); console.log(result);

MCP setup

MCP stands for Model Context Protocol. Ground Truth is a preflight service for unfamiliar external resources. Use the direct server for free checks and Stripe API-key access; use the separate xpay deployment for pay-per-call clients.

Claude Desktop

Add Ground Truth to ~/Library/Application Support/Claude/claude_desktop_config.json. No key is needed for the free first call.

{
  "mcpServers": {
    "ground-truth": {
      "url": "https://ground-truth-mcp.anishdasmail.workers.dev/mcp"
    }
  }
}

Cursor

Add Ground Truth to .cursor/mcp.json in your project or ~/.cursor/mcp.json globally. Add X-API-Key only for team-plan paid tools.

{
  "mcpServers": {
    "ground-truth": {
      "url": "https://ground-truth-mcp.anishdasmail.workers.dev/mcp"
    }
  }
}

PASS means the observed checks succeeded, WARN means the agent should inspect evidence or handle uncertainty, and FAIL means stop or choose another resource. None of these verdicts is a security guarantee.

Use cases

Ground Truth fits anywhere an AI agent needs a final check before sharing an answer or taking action.

Support

Verify pricing claims, confirm support entitlements, and check whether an API endpoint a customer asks about actually exists.

Product

Test market assumptions, check whether a competitor exists, and compare live pricing pages before you lock in a direction.

Compliance

Scan trust pages for SOC 2, ISO 27001, HIPAA, GDPR, DPA, SSO, and SCIM signals before repeating them to buyers or internal stakeholders.

Security & vendor diligence

Inspect public security headers, verify claims against public evidence, and add lightweight diligence before an agent recommends or approves a vendor.