web-data-plan-finderSAFE
Compare web scraping, crawling and SERP API pricing and limits against your workload and budget
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
MCP server that compares web scraping, crawling, SERP and headless browser API plans against your workload and conditions: the monthly cost of each plan for your volume, and whether each condition (budget, concurrent requests, JavaScript rendering, premium proxies, country targeting, billing of failed requests) is met, not met or unknown. Every stated value matches the provider's official pricing and documentation as of the check date given with it.
No API key or sign-up. The tools only read the plan list.
In a test of 30 questions (27 scored for cost) with gpt-5.6-sol (low), answers using this server had 3.6% plan cost errors vs 12.5% with web search alone (95% CI of the difference 1.3–15.9 points). Method, all results and limits: https://plans.intoperson.com/evidence/q3
Remote MCP server (Streamable HTTP): https://plans.intoperson.com/mcp
Official MCP registry name: io.github.scraping-api-plans/web-data-plan-finder
Connect
Claude Code
claude mcp add --transport http web-data-plan-finder https://plans.intoperson.com/mcp
Claude (Pro and Max plans)
Customize > Connectors, click "+", then "Add custom connector", and paste this URL:
https://plans.intoperson.com/mcp
ChatGPT (Plus, Pro, Business, Enterprise and Edu, on the web)
Settings > Security and login, turn on Developer mode. Then open ChatGPT Plugins, click "+", enter a name, choose "No Authentication", and paste this URL under Connection. In a chat, add the app from the tools menu:
https://plans.intoperson.com/mcp
Codex CLI
codex mcp add web-data-plan-finder --url https://plans.intoperson.com/mcp
Cursor (mcp.json)
{
"mcpServers": {
"web-data-plan-finder": {
"url": "https://plans.intoperson.com/mcp"
}
}
}VS Code (.vscode/mcp.json)
{
"servers": {
"web-data-plan-finder": {
"type": "http",
"url": "https://plans.intoperson.com/mcp"
}
10f1dc9cddedOBSERVED · 2026-10-11Trust audit
SAFEgrade B · trust 88/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
streamable-http
Gates applied: no_behavioural_pass, no_license.
10f1dc9cddedfull audit observations/trust-audit/mcp-server/scraping-api-plans__web-data-plan-finder.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 10f1dc9cdded | SAFE | B | 88 | first audit |
Questions
What is the web-data-plan-finder MCP server?
Compare web scraping, crawling and SERP API pricing and limits against your workload and budget
Is web-data-plan-finder safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (88/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does web-data-plan-finder need?
No credential environment variables were found in its source, so it appears to need none.
How does web-data-plan-finder run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (10f1dc9cdded), read on 2026-10-11. The repository is watched and re-audited when it changes.