Précis Finance MCP

Précis Finance MCP — Financial reporting on Databricks and ClickHouse

A read-only, self-hosted Model Context Protocol (MCP) server for financial reporting on Databricks or ClickHouse, built for Financial Planning & Analysis (FP&A) and management reporting. Give Claude, ChatGPT or another MCP-capable client access to governed metrics, financial statements, variance comparisons, row-level drill-down, charts and Excel exports from your own financial data. It is source-available under Elastic License 2.0 and forms the open core of Précis, the Finance Intelligence Platform.

You describe your business metrics once — KPIs, hierarchies, and financial-statement layouts in a YAML catalogue over a semantic layer of plain SQL views, versioned in git — and any MCP-capable client gets consistent, defensible numbers. Use your existing Databricks data model or start a local self-contained service with the bundled ClickHouse engine. Your own financials, not market data.

Use this if

• You run or support a finance function and want AI clients — Claude, ChatGPT, or any MCP-capable client — answering questions and pulling management reporting from your own numbers.
• You need governed metrics — one agreed definition of gross margin, utilisation, or revenue by business unit — not an agent querying raw rows in the general ledger or inventing its own definitions.
• You want it self-hosted, on infrastructure you already operate and under a security model you control — not another cloud contract.
• You need every answer traceable: read-only by construction, no figure generated by the model, every number aggregated from semantic views you can read.

Requirements

• Docker — Engine + Compose v2. Everything runs in containers; there is nothing else to install.
• No warehouse to provision — the stack bundles ClickHouse (the engine's analytical store), PostgreSQL (platform and artifact state), and Valkey (temporary snapshots). A local trial runs with nothing else and loads a sample finance model.
• Already run ClickHouse or Databricks? — optionally point the engine at your own instance instead of the bundled one; see ClickHouse data modes or Databricks setup.
• An MCP-capable client — Claude (claude.ai and Desktop connectors, against a deployed instance), Claude Code, ChatGPT, or any MCP client.
• Optional Excel access — the multi-user image also hosts the Précis Excel add-in at /excel; enable its OAuth client when you want live read-only workbook functions.

What Précis Finance MCP looks like

Every figure aggregates from the semantic views — account, cost centre, period, scenario — and the measures generic metric layers can't express (a utilisation denominator averaged across periods, re-aggregated by quarter or business unit, with subtotals in the layout) are first-class catalogue definitions.

Try the public demo

Connect a remote MCP client to https://mcp.precis.finance/mcp to explore Précis Finance MCP without installing anything or creating an account. The shared server exposes read-only tools over a synthetic finance dataset; it does not contain your financial data. No API key or sign-in is required.

For Claude Code:

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

Then ask precis_orientation what the demo supports, or request a P&L with comparatives. See the public demo connection guide for other MCP clients and the limits of this shared instance.

Quickstart — single-user local trial

export MCP_DEV_KEY=$(openssl rand -hex 32)

export ARTIFACT_SIGNING_KEY=$(openssl rand -hex 32) docker compose -f deploy/docker-compose.local.yml up -d --build docker compose -f deploy/docker-compose.local.yml exec precis-mcp \ python -m precis_mcp.sample_data # populate the demo model

One stack — the server plus ClickHouse, Postgres and Valkey — a shared dev key, bound to 127.0.0.1. Point any MCP client at http://127.0.0.1:8768/mcp with the dev key as bearer token. For example, with Claude Code:

claude mcp add --transport http precis http://127.0.0.1:8768/mcp \

--header "Authorization: Bearer $MCP_DEV_KEY"

Then ask a finance-specific question to prove this is not a generic SQL MCP: *"Show the P&L for FY2025 with comparatives."* · *"Drill revenue down by cost centre."* · *"Show utilisation by month for the Digital Transformation team."*

Full walkthrough, including the demo data and bringing your own model: docs/getting-started/quickstart.md.

Rather do this on a call? We pair with early adopters to stand Précis Finance MCP up against their own warehouse — precis.finance or hello@precis.finance.

Multi-user deployment

deploy/docker-compose.yml runs the multi-user stack — the open server, PostgreSQL, ClickHouse (if using the bundled deployment), Valkey, artifact storage, and OAuth 2.1 + PKCE sign-in. Deployment is modular along independent axes:

• Data — bundled ClickHouse (empty or with sample data), your own ClickHouse instance, or Databricks: ClickHouse data modes · Databricks setup
• Identity — local dev key, the bundled Keycloak (optionally federated to your IdP), or a direct external OIDC provider (Auth0 / Okta / Entra / Ping): docs/deployment/oauth-keycloak.md, docs/deployment/external-idp-recipes.md
• Ingress — the bundled Caddy proxy (bundled-proxy profile, on by default) terminates TLS with automatic Let's Encrypt certificates from nothing but PRECIS_DOMAIN. The app itself is proxy-agnostic: drop the profile to front it with an ingress you already operate (reference nginx vhost in deploy/nginx/, host helper scripts/install-precis-mcp.sh --nginx)
• Backups — additive backup compose profile: scheduled bundles (Postgres dump + ClickHouse backup + instance config) to a local volume or S3, with restore and drill commands: docs/operations/backups.md
• Excel add-in — optional hosted workbook functions served from the same instance at /excel; enable with the bundled Keycloak client or a public client in your external IdP: docs/excel/

scripts/deploy-mcp.sh --data-mode ... --auth-mode ... is the friendly front door over the Compose profiles. Every knob is an environment variable: docs/configuration/environment-variables.md.

Configure your data model

Your model lives in an instance/ directory — metric catalogue, semantic SQL views, ingestion bindings — and the bundled demo instance shows the shape. Start at docs/configuration/catalogue-and-semantic.md, then docs/configuration/ingestion.md and docs/operations/onboarding-ingestion.md to load your data. For Databricks, see the Databricks schema contract. The developer guide for adding server tools is docs/development/adding-read-tools.md.

Security and read-only posture

Start with the mechanisms, not the promise.

• Read-only by construction — the server retrieves; it never writes to or changes your source. There is no write path back.
• No figure is generated by the model — the agent requests defined metrics; Précis calculates and returns them using the agreed financial rules. Ask for utilisation by department and you get each department’s utilisation, with a total calculated using the same governed definition. Other agentic analytics approaches rely on agents writing SQL. When an agent writes SQL for each question, it must interpret how the measure should be calculated and aggregated, introducing opportunities for errors. Précis defines that logic once in the reporting engine and applies it consistently as the conversation develops. The agent retrieves the figures and narrates the results.
• Traceable to source — every number traces from response → semantic view → warehouse. The semantic views are plain SQL you can read; the catalogue is versioned in git.
• Your own warehouse, not market data — it runs in your environment, against your warehouse, under your own access controls.
• Identity — a local dev key, the bundled Keycloak (optionally federated to your IdP), or a direct external OIDC provider (Auth0 / Okta / Entra / Ping).
• Operator responsibility — Précis Finance MCP is designed to expose governed read operations; you still deploy and operate it under your own security model. Disclosure policy: SECURITY.md.

FP&A and financial reporting on Databricks

Use your existing Databricks environment as the analytical backend for Précis Finance MCP. Keep your financial data and pipelines in place, without copying the inputs into another analytical database.

Map your data to reporting views and agree the metric and statement definitions; finance can then request a monthly P&L, compare actuals with budget or drill into the drivers of a variance through a compatible MCP client.

What Précis adds alongside Databricks Genie: consistent financial calculations and presentation. Your agreed aggregation rules, statement layouts, comparison columns and number formats carry through each report. The agent requests established financial operations from the reporting engine, reducing repeated query generation and the scope for calculation errors as the investigation develops.

Our FP&A case study: Précis and Databricks Genie compares five financial requests against the same Databricks data, showing the differences in calculation fidelity, financial presentation and waiting time. Précis completed responses in 16–35 seconds, compared with 73–108 seconds for Genie in that session. The study compares the full Précis workspace with the native Genie interface; Finance MCP uses the same reporting engine, while response times depend on the connected client and deployment.

Read the Databricks product update for the broader platform benefits, including approved planning writeback. Précis Finance MCP remains read-only.

Documentation

Full documentation: docs.precis.finance.