Précis Finance MCP Server

by precis-finance Your server? Claim it

answering

Précis Finance MCP is answering right now. Last checked 3 min ago. It exposes 20 tools. Last commit 9 Oct 2026.

Public read-only Précis Finance MCP demo with synthetic data; no account or credentials required.

Uptime history 91 days of history

91 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

250 ms

Response time

average over 24h

Stars

last commit 9 Oct 2026

What changed 16

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 28 August 2026. No other catalogue keeps this.

9 Oct 4 tool descriptions were rewritten6 times that day run_metric, run_metric_data, run_statement and 1 more

9 Oct 5 tools changed the parameters they ask for inspect_rows, run_metric, run_metric_data and 2 more

9 Oct 3 tools appeared eval_chart_transform, export_dataset, get_file_download

24 Sep a tool changed version

28 Aug a tool changed version

and 2 more, back to 28 August 2026

What the code does

We read the source, 1 d ago · tools taken from the live server · rules 995398eba69f

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

Claims read-only, but the code runs commands precis_mcp/backup/restore.py:151, precis_mcp/backup/runner.py:90, precis_mcp/observability.py:164 и ещё 1

    proc = subprocess.run(

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command precis_mcp/backup/restore.py:151, precis_mcp/backup/runner.py:90, precis_mcp/sample_data/generate.py:126

    proc = subprocess.run(

Builds a file path from a variable precis_mcp/ingestion/wiring.py:186

        return os.path.join(upload_root, prefix)

Executes code built at runtime precis_mcp/observability.py:164

            mod = __import__(mod_path, fromlist=[cls_name])

Page loads a third-party script excel-addin/src/auth-callback/auth-callback.html:8, excel-addin/src/taskpane/taskpane.html:10

    <script type="text/javascript" src="https://appsforoffice.microsoft.com/lib/1/hosted/office.js"></script>

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Précis Finance MCP and you get told the day something new turns up.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 3 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add precis-finance-mcp --transport http https://mcp.precis.finance/mcp

Settings → Connectors → Add custom connector, then paste this address

https://mcp.precis.finance/mcp

~/.codex/config.toml

[mcp_servers.precis-finance-mcp]
url = "https://mcp.precis.finance/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "precis-finance-mcp": {
      "url": "https://mcp.precis.finance/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "precis-finance-mcp": {
      "type": "http",
      "url": "https://mcp.precis.finance/mcp"
    }
  }
}

Available tools 20

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

inspection

get_inspection_schema

Get the column schema for an inspection source.

list_inspection_sources

List the row-level sources available for inspection.

load

get_load_status

Fetch one data load's full detail by load_id — timestamps, status, rows landed, and any error message.

list_load_history

List data-load attempts from the ingestion audit trail — when each dataset landed, with what status. Answers "is April in yet?" / "when was this data last loaded?".

metric

run_metric

Break one or more metrics down by a dimension — revenue by project, utilisation by employee, headcount trends, GL account drill-down. Rows are the dimension; columns are metrics × scenarios. Pass `scenarios` explicitly and give every scenario a concise, user-facing `alias` such as Actuals, Budget, Variance, or Var %. Returns a formatted table with structured data. The widget already displays this table to the user. Add useful interpretation; do not reproduce the table or restate all its rows in Markdown unless the user explicitly requests it or the widget is unavailable.

run_metric_data

Break one or more metrics down by a dimension — revenue by project, utilisation by employee, headcount trends, GL account drill-down. Rows are the dimension; columns are metrics × scenarios. Pass `scenarios` explicitly and give every scenario a concise, user-facing `alias` such as Actuals, Budget, Variance, or Var %. Returns the raw figures (and a `data_ref`) for your own analysis or to build a chart — pass `[data_ref]` as `data_refs` to eval_chart_transform. Does not show the user a table.

statement

run_statement

Run a financial statement — P&L, variance report, or executive summary. Rows are statement lines (Revenue, Direct Cost, Gross Margin, …); columns are scenarios. Supports an optional dimension breakdown (e.g. by period or cost centre). For an unspecified general P&L, prefer `full_pnl` when it is listed by precis_orientation. Give every scenario a concise, user-facing `alias` such as Actuals, Budget, Variance, or Var %. Returns a formatted table with structured data. The widget already displays this table to the user. Add useful interpretation; do not reproduce the table or restate all its rows in Markdown unless the user explicitly requests it or the widget is unavailable.

run_statement_data

Run a financial statement — P&L, variance report, or executive summary. Rows are statement lines (Revenue, Direct Cost, Gross Margin, …); columns are scenarios. Supports an optional dimension breakdown (e.g. by period or cost centre). For an unspecified general P&L, prefer `full_pnl` when it is listed by precis_orientation. Give every scenario a concise, user-facing `alias` such as Actuals, Budget, Variance, or Var %. Returns the raw figures (and a `data_ref`) for your own analysis or to build a chart — pass `[data_ref]` as `data_refs` to eval_chart_transform. Does not show the user a table.

binding

get_binding

Fetch one data feed's full configuration: source, target dataset, schedule, and extract parameters.

bindings

list_bindings

List the configured data feeds (ingestion bindings) with their schedule — which datasets load, from where, how often.

dimensions

list_dimensions

List the dimensions defined in the model — keys, labels, and kinds (leaf / derived / ragged hierarchy). Catalogue metadata only; use search_hierarchy to list a dimension's members.

eval

eval_chart_transform

Create a chart from data_refs (an array of snapshot IDs), a bounded JavaScript function, and chart_spec. Supports line, bar, area, waterfall, scatter, horizontal_bar, forecast_line, cohort_heatmap and sparkline_row. Query first and inspect rows; the transform takes one result per ref and returns flat rows.

export

export_dataset

Export a cached data_ref to json or xlsx without rerunning the query; returns a temporary file and download link.

file

get_file_download

Renew a download capability for an available, owned artifact.

hierarchy

search_hierarchy

Search the dimension hierarchies (cost centres, accounts, …) to find valid codes and ids before composing a query.

inspect

inspect_rows

Inspect the row-level detail behind a figure, from an enabled inspection source. Returns a capped sample for reasoning plus a grid for the user.

kpis

list_kpis

Browse the metric catalogue — metric keys, formats, domains, and the dimensions available per metric.

precis

precis_orientation

Call this first. Returns how to use Précis over this connector: the data model (scenarios, metrics, statements, dimensions), the reporting-tool variants, and how to build charts. Read it before composing queries.

scenarios

list_scenarios

List the available planning scenarios and their status.

variants

list_variants

List the what-if variants of a scenario.

Endpoints

URL	Transport	State	Latency	Checked
https://mcp.precis.finance/mcp	streamable-http	answering	248 ms	3 min ago

Alternatives to Précis Finance MCP

same job, measured the same way

PolyAccounts synthetic accounting demo

by andrewblount

Synthetic accounting MCP demo with exact balances and ledger evidence. No account or API key.

local only

Trovest Financial Data

by trovest

Financials, ratios, SEC filings and analyst data for any public company. Premium account required.

answering

Binance Market MCP

by mrfentmen

Live crypto prices, tickers, and candlestick charts from Binance public data. No key required.

533 installs/wk local only

Financier docs

by financier

Search and read Financier's developer documentation. No credentials needed.

2 tools answering

ARKOSCOPE Public Sources

by arkoscope

Read-only, dated public crypto source registry with evidence status. Local stdio; no API keys.

local only

FIMA MCP

by tryfima

Read-only financial reports for projects the authenticated FIMA user is authorized to access.

answering

Fec MCP

by mrfentmen

US campaign finance data from the FEC. No key required.

103 installs/wk local only

Openfinance Br MCP

by brunovicco

Secure Open Finance Brasil MCP server with typed tools and a credential-free mock mode

90 installs/wk local only

Précis Finance MCP — questions

Answers built from our own checks of this server.

What can Précis Finance MCP do?

It exposes 20 tools, read directly from the server on our last check. Among them: eval_chart_transform, export_dataset, get_binding, get_file_download, get_inspection_schema, get_load_status and 14 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

What is Précis Finance MCP mostly used for?

Its tools cluster around metric, statement and inspection. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.

Is Précis Finance MCP working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 250 ms. The bar chart above shows every period we have measured.

How do I connect Précis Finance MCP?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Précis Finance MCP need an API key?

No. Précis Finance MCP completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 20 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Précis Finance MCP?

It answers our handshake in 250 ms on average, which is faster than 57% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Précis Finance MCP open source?

We cannot say either way: written in Python and 7 stars on GitHub, but we could not determine the licence, and without one the code is not open source by default.