Code agentAny MCP client
Build-test-deploy engineering: CI wall clock, bottleneck forecast, staged rollout, rollback point, runbook.
↓ 1★ 0Free
Browse › Software Development › AI Visibility Tracker
DoerScanned & human-reviewedAny MCP client
AI Visibility Tracker
Asks the assistants your buyers ask, and reports what they say about you.
Software DevelopmentE-commerceDev Productivity & Project OpsDocumentation & KnowledgeReview & Reputation Management@katateam
Before you connect: what this agent would do
A preview derived from this agent’s definition — not a live run. Nothing runs and no key is sent until you connect. FindAgent runs it on the hosted connection.
Tools it can use (3)
- ask_claudeCan change data
Put one buying question to Claude and return the answer verbatim for scoring.
Reaches: api.anthropic.com
Uses your Anthropic API key.
- ask_openaiCan change data
Put the same question to an OpenAI model, so the finding is not single-vendor.
Reaches: api.openai.com
Uses your OpenAI API key.
- score_mentionRead-only
Turn one raw model answer into a structured record: appearance, position, claims, competitors.
Credentials it will ask for (2)
- Anthropic API key
Only ever sent to: api.anthropic.com
Format: Enter just the key value — FindAgent sends it as the x-api-key header.
- OpenAI API key· optional
Only ever sent to: api.openai.com
Safety rails that guard it
- Every result is scanned for leaked secrets and prompt-injection before it reaches you — a check no agent can turn off.
- These personal details are removed from your input before the agent sees them: Credit card, IBAN, National ID, Email, Phone.
- These personal details are stripped from the agent’s results before you see them: Email, Phone.
- A request larger than 40,000 characters is rejected before it runs.
- ask_claudeRate limited to 120/hour.
- ask_openaiRate limited to 120/hour.
- score_mentionRate limited to 300/hour.Safe to retry automatically if a run is interrupted.
Run locally
This MCP server runs on your own machine — FindAgent only points you at it. Run the command below, then add it to your MCP client. Nothing is hosted or proxied on our side.
terminal
npx -y @findagent/mcp runAdd it to your MCP client
Paste this into your client config (e.g. claude_desktop_config.json or a Cursor mcp.json), then restart the client.
mcp client config
{
"mcpServers": {
"ai-visibility-tracker": {
"command": "npx",
"args": [
"-y",
"@findagent/mcp",
"run"
]
}
}
}What you'll need — and where to get it
This agent will ask you for the following. You enter them when you connect — they're encrypted and never shared with the creator.
Anthropic API key
An Anthropic API key from console.anthropic.com. Paste the bare key - the runtime sends it in the x-api-key header. Probe questions consume tokens, so set a spend limit on the key.
Create a key on the Anthropic Console API keys page (console.anthropic.com → API keys).
Paste the value as a single line.
Only sent to: api.anthropic.com
OpenAI API key · optional
An OpenAI API key. Optional - without it the tracker reports from one vendor only, which is weaker evidence but still usable. Set a spend limit on the key.
Create a secret key on the OpenAI API keys page (platform.openai.com → API keys).
Paste the value as a single line.
Only sent to: api.openai.com
Requirements
- This server requires authentication — see the description for how to get a key.
Related agents
CompareCode agentAny MCP client
Whose failure is this, and do these tests catch anything, from the CI, coverage and mutation evidence you paste.
↓ 1★ 0Free
Code agentAny MCP client
Keeps asking until a request is genuinely buildable, then writes the use case, criteria and ticket drafts.
↓ 1★ 0Free
Code agentAny MCP client
Turns an approved design into a typed component with its story, test, API contract and client SDK.
↓ 1★ 0Free
Code agentAny MCP client
Maps your module graph, scores blast radius, plans migrations and composes a validated unified diff.
↓ 1★ 0Free
Code agentAny MCP client
Decides whether a change can merge: diff review, test evidence, breaking-change and tech-debt scoring.
↓ 1★ 0Free
More from @katateam
DoerAny MCP client
Sprint health, backlog hygiene, and an exec brief — from one Jira read, without managing anyone.
↓ 1★ 0Free
MCP serverAny MCP client
Manage Heroku apps, dynos, add-ons, Postgres, and pipelines.
MCP serverAny MCP client
Search Shopify's developer docs and validate your GraphQL and theme code.