Précis Finance MCP
Public read-only Précis Finance MCP demo with synthetic data; no account or credentials required.
Connector by precis-finance · GitHub account verified by the MCP Registry
Install
Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install connector/precis-finance-precis-finance-mcp
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Remote endpoint
https://mcp.precis.finance/mcpRemote (HTTP)
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 25, 2026.
- Tools
- 18 read · 2 write · 0 delete
- Secrets
- None asked for
- Install scripts
- Nothing to install (hosted)
- Runs as
- Hosted (remote endpoint)
Tools by what they do 20
From the running server's own tool list (tools/list) on Oct 25, 2026.
Read 18 · Look things up without changing anything.
eval_chart_transformget_bindingget_file_downloadget_inspection_schemaget_load_statusinspect_rowslist_bindingslist_dimensionslist_inspection_sourceslist_kpislist_load_historylist_scenarios
Show 6 more tools
list_variantsrun_metricrun_metric_datarun_statementrun_statement_datasearch_hierarchy
Write 2 · Create, change, send or run things.
export_datasetprecis_orientation
Network hosts it talks to 6
appsforoffice.microsoft.com· found in codedocs.precis.finance· found in codedownload.docker.com· found in codegithub.com· found in codemcp.precis.finance· found in remote endpoint, install command, codeprecis.finance· found in code
Files it touches
/opt/precis-mcp/var/lib/precis/ingest/uploads
Tools (20)
As the server listed them on Oct 25, 2026. Descriptions are the server’s own words; hidden characters are shown as [U+…].
eval_chart_transformread-onlyCreate 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_datasetExport a cached data_ref to json or xlsx without rerunning the query; returns a temporary file and download link.
get_bindingread-onlyFetch one data feed's full configuration: source, target dataset, schedule, and extract parameters.
get_file_downloadread-onlyRenew a download capability for an available, owned artifact.
get_inspection_schemaread-onlyGet the column schema for an inspection source.
get_load_statusread-onlyFetch one data load's full detail by load_id — timestamps, status, rows landed, and any error message.
inspect_rowsread-onlyInspect the row-level detail behind a figure, from an enabled inspection source. Returns a capped sample for reasoning plus a grid for the user.
list_bindingsread-onlyList the configured data feeds (ingestion bindings) with their schedule — which datasets load, from where, how often.
list_dimensionsread-onlyList 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.
list_inspection_sourcesread-onlyList the row-level sources available for inspection.
list_kpisread-onlyBrowse the metric catalogue — metric keys, formats, domains, and the dimensions available per metric.
list_load_historyread-onlyList 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?".
list_scenariosread-onlyList the available planning scenarios and their status.
list_variantsread-onlyList the what-if variants of a scenario.
precis_orientationCall 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.
Show 5 more tools
run_metricread-onlyBreak 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_dataread-onlyBreak 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.
run_statementread-onlyRun 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 …
run_statement_dataread-onlyRun 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.
search_hierarchyread-onlySearch the dimension hierarchies (cost centres, accounts, …) to find valid codes and ids before composing a query.
Compare and alternatives
Featured in
Signals
- Stars
- 7
- Forks
- 0
- Open issues
- 0
- Last commit
- Oct 9, 2026 (19 days ago)
- Last release
- Oct 9, 2026 (19 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
io.github.precis-finance/precis-finance-mcp- Version
- 0.3.0
- Auth
- Auth not stated
- License
- License unknown
- Website
- precis.finance/mcp
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Cite this page
Précis Finance MCP. Agent Mart. https://agentmart.dev/connectors/precis-finance-precis-finance-mcp (last updated 2026-10-24)