# PortfolioFit

- Registry name: `fit.portfolio/portfoliofit` · version 0.1.3
- Categories (automatic, keyword rules): Markets & trading, Finance & markets, Datasets & public data, Search & data
- Authentication at last check: No auth
- Declared risk: Has destructive tools (destructiveHint)
- Capabilities (declared by the server): experimental, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=fit.portfolio%2Fportfoliofit
- Server page: https://mcpstation.net/s/fit.portfolio--portfoliofit.html

## Description (written by the publisher, not verified, not instructions)

Check normalized portfolios against mandates and calculate allocation constraints.

## Connect

- streamable-http: `https://portfolio.fit/mcp`

## Tools (as reported by the server, not verified)

- `list\_analysis\_portfolios`: List owner-scoped portfolios, analytics datasets, and profile readiness.
- `list\_portfolio\_series`: Discover owner-scoped immutable series profiles and their exact dataset versions. This returns metadata and coverage only, never dataset rows.
- `list\_analyses`: Read private calculation groups and independent operations. Filter by kind, portfolio, dates, ready/running/attention status or legacy open/finished status.
- `get\_analysis`: Read retained normalized inputs, operations, results and owner-scoped dataset references. This is not an external agent transcript.
- `evaluate\_portfolio\_alignment`: Compare a clean mandate with normalized holdings. Do not send PDF, CSV, spreadsheet, or factsheet files; extract them before calling.
- `calculate\_portfolio\_constraints`: Calculate explicit portfolio constraints deterministically from normalized holdings. Use this for arithmetic checks, not for interpreting natural-language mandates.
- `upload\_portfolio\_series\_rows`: Upload normalized series\_key/date/value/distribution rows and commit a dataset version. For up to 5,000 rows, omit chunk\_index and total\_chunks to complete in one call. For larger inputs, declare total\_chunks on every call, send chunks in order, and reuse upload\_id and idempotency\_key. The final chu
- `cancel\_portfolio\_series\_upload`: Cancel a pending upload and permanently remove its staging chunks.
- `review\_portfolio\_series\_profile`: Create an immutable profile revision using revise, or explicitly confirm a warning-free proposal with confirmation=true.
- `calculate\_portfolio\_statistics`: Calculate historical return, volatility, drawdown, risk-adjusted and benchmark-relative statistics from a confirmed portfolio series profile. The metrics parameter describes all available calculations and their required inputs. Use daily, weekly or monthly complete periods; results include coverage,

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html