
Policy Pal MCP server
Which MCP servers are Policy Pal's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-27
- Registry namelink.policypal/policypalverified in the MCP registry
The registry name sits under policypal.link. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-27
- Tools3
- Server calls itselfpolicypal
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 181 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer179 ms
- Space in an agent's context≈ 1,082 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
- Not saying whether it only reads or can destroy: 3 of 3
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
check_policyRead one privacy policy or terms-of-service page and return a grounded verdict, eight fixed yes/no/partly/not-stated answers, and up to five findings, each with a verbatim quote from the document. Use this instead of fetching and reading…
compare_policiesAnswer the same eight fixed questions across two to five services at once, so their policies can actually be compared. Use this instead of reading each document yourself. Doing it yourself needs N full reads and a rubric you have to keep…
policy_changes_sinceSay what changed in a service's policy since a date, expressed as changes to the eight fixed answers. You cannot do this yourself at any context size: it needs the earlier version of the document, and the earlier version is gone from the…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"policypal": {
"type": "http",
"url": "https://api.policypal.link/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http policypal https://api.policypal.link/mcpclaude.ai, ChatGPT and other clients: add https://api.policypal.link/mcp as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.