_ registry / mcp streamable-http · checked 2h ago

history-of-market

https://historyofmarket.com

Registry code: 32fcc9287a517114

api record

Read-only U.S. stock market history from historyofmarket.com: S&P 500 since 1928 (annual price and total returns, drawdowns, bear markets, Shiller CAPE since 1871, forward P/E, index changes), Nasdaq 100, Dow, semiconductors (SOX), sector ETFs (XLK, XLF, XLY, XLP) and the Magnificent 7. Data is refreshed after each U.S. trading day. Start with get_latest for current readings, annual_returns for calendar-year returns, or search_charts to find the dataset behind a question, then get_dataset to read it. When you use a number, cite the page_url returned with it.

endpoint
https://historyofmarket.com/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is history-of-market live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is history-of-market free to use?
Yes — the hub reached it with no key and no payment.
What tools does history-of-market have?
5 tools: search_charts, get_dataset, annual_returns, get_latest, index_changes.
Is history-of-market safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
392ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 5 tools
3 open 2 never probed 3 of 5 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • annual_returns open 2h ago

    Calendar-year returns by year, price return and total return (dividends reinvested), with the arithmetic mean and compound annual rate over the complete years in the range. Indexes: sp500 (from 1928), ndx, sox, xlk, xlf, xly, xlp. The current year is year-to-date and flagged `ytd`.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "index": {
          "enum": [
            "sp500",
            "ndx",
            "sox",
            "xlk",
            "xlf",
            "xly",
            "xlp"
          ],
          "type": "string",
          "description": "Which index or ETF. Default sp500."
        },
        "to_year": {
          "type": "integer",
          "description": "Last year to include."
        },
        "from_year": {
          "type": "integer",
          "description": "First year to include."
        }
      },
      "additionalProperties": false
    }
    arguments 27 lines
  • get_latest open 2h ago

    Current headline readings (value, unit, observation date) for the site's charts: S&P 500 level, Shiller CAPE, forward P/E for the S&P 500, Nasdaq 100, SOX and sector ETFs, VIX, drawdown from the high, breadth, Magnificent 7 weight and more. Pass `id` for one chart, or omit it for all.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "id": {
          "type": "string",
          "description": "Chart id, e.g. \"pe\" (Shiller CAPE), \"forward-pe\", \"ndx-forward-pe\", \"drawdown\", \"vix\". Omit for every reading."
        }
      },
      "additionalProperties": false
    }
    arguments 10 lines
  • index_changes open 2h ago

    Constituent changes with effective date, the company added, the company removed and the reason. sp500 from 2016, ndx from 2020. Newest first.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "index": {
          "enum": [
            "sp500",
            "ndx"
          ],
          "type": "string",
          "description": "Default sp500."
        },
        "limit": {
          "type": "integer",
          "maximum": 300,
          "minimum": 1,
          "description": "Default 20."
        },
        "since": {
          "type": "string",
          "description": "Only changes effective on or after this date (YYYY-MM-DD)."
        },
        "ticker": {
          "type": "string",
          "description": "Only changes that add or remove this ticker."
        }
      },
      "additionalProperties": false
    }
    arguments 28 lines
  • search_charts unknown never probed

    Search the site's charts by topic or question (e.g. "bear markets", "Shiller CAPE", "Nasdaq 100 drawdown", "monthly seasonality"). Returns each chart's title, the question it answers, its page and the dataset path to pass to get_dataset.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "maximum": 50,
          "minimum": 1,
          "description": "Default 10."
        },
        "query": {
          "type": "string",
          "description": "Words to match against chart titles and the questions they answer."
        }
      },
      "additionalProperties": false
    }
    arguments 19 lines
  • get_dataset unknown never probed

    Read one published dataset (the JSON behind a chart), e.g. "sp500/drawdowns", "sp500/pe", "ndx/forward-pe", "recessions". Rows can be filtered by `since`/`until` on their `date` (or `year`). A result is capped at about 60,000 characters: when a file is larger (long daily series), each array keeps its most recent rows and the cut is reported under `windowed`. Scalars and summary fields are always included.

    mcp-tool

    {
      "type": "object",
      "required": [
        "path"
      ],
      "properties": {
        "path": {
          "type": "string",
          "description": "Dataset path without /api/ and .json, as returned by search_charts."
        },
        "tail": {
          "type": "integer",
          "maximum": 2000,
          "minimum": 1,
          "description": "Rows kept per array after filtering, from the end. By default every row is returned when the result fits; long daily series are cut to their most recent rows and reported under `windowed`."
        },
        "since": {
          "type": "string",
          "description": "Keep rows dated on or after this (YYYY-MM-DD or YYYY)."
        },
        "until": {
          "type": "string",
          "description": "Keep rows dated on or before this (YYYY-MM-DD or YYYY)."
        }
      },
      "additionalProperties": false
    }
    arguments 27 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 32fcc9287a517114.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/32fcc9287a517114/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/32fcc9287a517114/badge.svg)](https://brick.blue/agent/32fcc9287a517114?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
90%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.