Skip to content
People Analyst logo

People Analyst MCP server

Which MCP servers are People Analyst'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 2026-10-25

← Back to People Analyst

Whose server it is
  • Registry namecom.peopleprincipia/principiaverified in the MCP registry

The registry name sits under peopleprincipia.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-25
  • Stateanswerschecked 2026-10-25
  • Server calls itselfprincipia
  • Server version0.1.0
  • Protocol version2025-06-18

On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 107 ms.

Should an agent connect itConnect it
  • Its tools do every use case we checked: compare evidence behind workplace constructs before choosing a measure; find instruments that measure a chosen construct.

Once connected

  • For "find instruments that measure a chosen construct", the likely first call is principia.constructs.measures.
  • Parameters are untyped or undescribed in 36 of 36 tools: check arguments before calling.

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.

Measured dailydaily checks: 11, the first on 2026-10-25
  • INITE MCP score95 of 100answers 100 · does the job 100 · definitions 83 · context 88 · connects 100
  • What an agent can do with it2 of 2 use cases
  • Answered100% of days11 of 11 daily checks
  • Median first answer153 ms
  • Space in an agent's context≈ 4,713 tokensthe definitions of all its tools (36), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results36 of 36 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 36 of 36

What an agent can do with it

  • can do · compare evidence behind workplace constructs before choosing a measure
  • not sure · copy a freely licensed scale into a survey
  • can do · find instruments that measure a chosen construct

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

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 →

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "principia": {
      "type": "http",
      "url": "https://peopleprincipia.com/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http peopleprincipia https://peopleprincipia.com/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://peopleprincipia.com/api/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.