Skip to content
PtData logo

PtData MCP server

Which MCP servers are PtData'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 2026-10-30

← Back to PtData

Whose server it is
  • Registry nameio.ptdata/ptdataverified in the MCP registry

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

When we asked itchecked 2026-10-30
  • Stateanswerschecked 2026-10-30
  • Tools4
  • Server calls itselfptdata
  • Server version3.3.2
  • Protocol version2025-06-18

On 2026-10-30 the server answered initialize and tools/list without a sign-in. First answer in 232 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: Query fiscal figures as they were known on a past date; Rebuild historical index membership without survivorship bias; Give AI agents point-in-time financial data via MCP.
  • Checked on 4 of the 7 days it takes to judge reliability.

Once connected

  • For "Query fiscal figures as they were known on a past date", the likely first call is get_fundamentals.
  • For "Rebuild historical index membership without survivorship bias", the likely first call is get_index_constituents.
  • For "Give AI agents point-in-time financial data via MCP", the likely first call is get_fundamentals.
  • Parameters are untyped or undescribed in 4 of 4 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: 4, the first on 2026-10-30
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring4 of the 7 daily checks it takes to print a share
  • Median first answer214 ms
  • Space in an agent's context≈ 585 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results4 of 4 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 4 of 4

What an agent can do with it

  • can do · Query fiscal figures as they were known on a past date
  • can do · Rebuild historical index membership without survivorship bias
  • can do · Give AI agents point-in-time financial data via MCP

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 →

Tools it offers4 tools · read 2026-10-30
  • get_index_constituents

    S&P 500 (or other index) constituents as understood on `as_of_date` (YYYY-MM-DD), survivorship-free. Point-in-time, with lineage.

  • get_fundamentals

    Point-in-time fundamentals for `ticker` as known on `as_of_date` (YYYY-MM-DD). Returns each available metric's value for the fiscal period with source + knowledge time + lineage under `metrics`. Any requested metric with no value appears…

  • get_filing_metadata

    SEC filings for `ticker` available on `as_of_date`, newest first, with amendment linkage.

  • get_earnings_event

    Earnings event: 8-K acceptance timestamp, as-reported figures, and the derived realized price reaction. `fiscal_period` is FY or Q1..Q4.

How to connect

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

{
  "mcpServers": {
    "ptdata": {
      "type": "http",
      "url": "https://api.ptdata.io/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http ptdata https://api.ptdata.io/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://api.ptdata.io/mcp as a custom connector in the settings.

OpenAPI spec

4 paths, read 2026-10-30. Open the spec ↗

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.