MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Payments & trading

Portfolio Terminal

Dated ETF, stock and calendar data, plus tax-loss, withholding and fee math on your holdings.

Checks passed
13 / 22

1 failed · 8 not measured

Median response
573 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
10

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Outdated check

Last connection measurement is over 24 hours old. Current availability is unknown.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
312

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 573 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name portfolio-terminal.

  • Pass
    Lists tools

    tools/list returned 10 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 573 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 573 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    31 of 31 parameters have a description (100%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-11-01T12:47:49.506396Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using Portfolio Terminal

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

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

Capabilities

Tools 10

analyze_ticker

Dated key facts and a plain-English chart read for one ticker Portfolio Terminal covers (390 US stocks, 30 ETFs, 17 cryptocurrencies and 4 commodity futures): price and one-year change, 52-week range, distance from the 200-day average, 30-day volatility with a risk rating, P/E and dividend yield, all-time high and "lowest since", ten years against the S&P 500 (SPY), support and resistance levels, which tracked ETFs and famous investors (13F) hold it, and related research. Use it for "how is NVDA doing", "is TSLA near its high", "what does the AAPL chart say".

Discovered
compare

Five-year head-to-head of two covered stocks or ETFs from weekly closes adjusted for dividends and splits: total and annualized return, 1-, 3- and 5-year returns, volatility, worst drawdown and worst week, correlation, what $10,000 became, plus each one's dividend yield, beta and (for funds) fee. Use it for "SCHD vs VIG", "NVDA vs AMD".

Discovered
dividend_calendar

US stocks and ETFs (of the 420 Portfolio Terminal covers) going ex-dividend in a month or a date range: ex-dividend date, pay date, dividend per share, yield, frequency, and whether the date is confirmed by the company or estimated from its payment rhythm. Buy before the ex-date to receive the dividend. Filter by one ticker with `symbol`.

Discovered
earnings_calendar

US companies (of the 390 Portfolio Terminal covers) reporting earnings in a month or a date range: the day, before the open or after the close, EPS and revenue estimates, whether the date is confirmed or estimated, and once out, the result against the consensus and how many recent quarters beat it. Filter by one ticker with `symbol`.

Discovered
etf_holdings

An ETF's or index fund's holdings from the issuer's full file (or its latest SEC N-PORT report for funds outside the catalog): the largest lines with their weights, the sector mix, and how concentrated it is (weight of the top 10, how many names make up half the fund, effective number of holdings). Share classes of one fund (VFIAX → VOO) resolve to its file.

Discovered
etf_overlap

How much of two ETFs is the same money: overlap by weight (the sum, over companies both hold, of the smaller of the two weights), how many companies they share, what share of each fund sits in names the other also holds, and the largest shared holdings. Full issuer files, matched on ISIN. Use it for "VOO vs QQQ overlap", "is IVV the same as VOO".

Discovered
fund_fees

Computes, on the funds and amounts the user gives, what each fund's expense ratio takes a year (amount × expense ratio), the total and the weighted ratio, with the expense ratios of Portfolio Terminal's fees view (the fund's latest annual report as Yahoo Finance lists it). A fact, not a verdict: no other fund is suggested. A line that is not a fund, or whose ratio is not published, is named. Nothing is stored. Use it for "how much do my ETFs cost me a year".

Discovered
tax_loss_harvest

Computes, on the lots the user gives (ticker, shares, price, date, account and its type), the losses a sale before December 31 would realize and what they offset, with the engine of Portfolio Terminal's "Before December 31" panel. US resident: FIFO lots per account, short vs long term, this year's realized gains, the year netted as Schedule D nets it (the $3,000 off ordinary income, the carryforward), and the wash-sale rule across every account, IRA and 401(k) included: losses it took this year, windows still open, and the first day the same security can be bought back without one (IRS Publication 550). French resident: weighted average cost across accounts at ECB rates, PEA and crypto left out, and the flat tax those losses erase against this year's net gains (CGI art. 150-0 D, 200 A). Funds on the same index are flagged, never judged "substantially identical". Current prices are fetched unless given in `prices`. Nothing is stored. Use it for "how much tax can my losses save before December 31", "would this be a wash sale".

Discovered
who_holds

Which of the 54 tracked US ETFs hold a US-listed stock (weight and rank, from each issuer's full holdings file, matched on ISIN), and which famous investors hold it in their latest SEC Form 13F (share of their reported portfolio, rank, quarter). Offline data: fast, no market call. Use it for "which ETFs hold PLTR", "does Buffett own Apple".

Discovered
withholding_check

Computes, on the dividends the user gives (a year of dividends, gross, by payer: a ticker such as "NESN.SW" or a country code), the tax each payer's country keeps at source, the treaty rate, and what was withheld above it over 12 months, which only that country refunds on a claim; for a French resident, also the treaty part France credits on form 2047. Same engine as Portfolio Terminal's Income and Pro tabs: statutory rates as of 2026, a US dividend at 15% (W-8BEN on file), European-listed funds paying no withholding. Countries outside its table are named, never guessed. Nothing is stored. Use it for "how much Swiss tax do I lose on Nestlé dividends", "which of my dividends are over-withheld".

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected573 ms10