Skip to main content
Glama

tacit-mcp

MCP server that connects AI assistants to Tacit building digital twins. Ask questions about your buildings, equipment, sensors, and zones in natural language.

Works with Claude Desktop, Claude Code, Cursor, Windsurf, and any MCP-compatible client.

What it does

Four read-only tools:

Tool

Purpose

tacit_list_sites

List buildings your API key can access

tacit_graphql

Query the building knowledge graph (Brick-compliant)

tacit_timeseries

Fetch historical sensor data

tacit_list_files

List documents and files for a site

The GraphQL tool includes the full schema reference, so the AI model can compose queries without needing separate documentation.

Related MCP server: skyspark-mcp

Quick start

npx -y @tacit/mcp-server

Just point your MCP client at it (see configuration below). No cloning, no building.

Option B: Clone and build

git clone https://github.com/ucl-sbde/tacit-mcp.git
cd tacit-mcp
npm install
npm run build

You'll need a Tacit API key. Get one from your dashboard at app.betacit.com under Site Settings > API Keys.

Connection methods

1. Stdio transport (local, default)

The standard method — the MCP client launches the server as a child process. Best for individual use on your own machine.

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "tacit": {
      "command": "npx",
      "args": ["-y", "@tacit/mcp-server"],
      "env": {
        "TACIT_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Code

Add to .mcp.json in your project:

{
  "mcpServers": {
    "tacit": {
      "command": "npx",
      "args": ["-y", "@tacit/mcp-server"],
      "env": {
        "TACIT_API_KEY": "your-api-key"
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "tacit": {
      "command": "npx",
      "args": ["-y", "@tacit/mcp-server"],
      "env": {
        "TACIT_API_KEY": "your-api-key"
      }
    }
  }
}

2. Streamable HTTP transport (remote)

Run the server as a persistent HTTP service. Best for teams, cloud deployments, and environments where users can't install Node.js locally.

# Start the HTTP server
TACIT_API_KEY=your-api-key npm run start:http

# Or with npx
TACIT_API_KEY=your-api-key npx --package @tacit/mcp-server tacit-mcp-http

The server listens on http://0.0.0.0:3001/mcp by default.

Connect from any MCP client

Point your client at the server URL with a bearer token:

{
  "mcpServers": {
    "tacit": {
      "type": "streamable-http",
      "url": "https://your-host:3001/mcp",
      "headers": {
        "Authorization": "Bearer your-api-key"
      }
    }
  }
}

HTTP configuration

Variable

Default

Description

PORT

3001

Port to listen on

HOST

0.0.0.0

Bind address

MCP_PATH

/mcp

MCP endpoint path

TACIT_API_KEY

Required in API key mode

TACIT_OAUTH_ISSUER

Set to enable OAuth 2.1 mode

Health check

GET /health → { "status": "ok", "transport": "streamable-http", "sessions": 3 }

3. OAuth 2.1 (enterprise)

For production deployments where you want users to authenticate via Tacit's login flow instead of managing API keys:

TACIT_OAUTH_ISSUER=https://app.betacit.com npm run start:http

This enables:

  • Dynamic client registration — MCP clients register automatically

  • Authorization code + PKCE — users log in through Tacit's web UI

  • Token refresh — sessions stay alive without re-authentication

  • Token revocation — clean session termination

MCP clients that support OAuth (like Claude Desktop) will discover the auth configuration automatically via the .well-known/oauth-authorization-server metadata endpoint.

4. Docker

docker run -p 3001:3001 -e TACIT_API_KEY=your-api-key tacit/mcp-server

Connect using the HTTP transport config above.

Try it

Once connected, ask your AI assistant things like:

  • "List all my building sites"

  • "What AHUs are in Tower West?"

  • "Show me temperature sensors on AHU-001"

  • "Get the last 24 hours of supply air temperature data"

  • "What equipment feeds the lobby zone?"

Environment variables

Variable

Required

Default

Description

TACIT_API_KEY

Yes (stdio/HTTP)

Your Tacit API key

TACIT_API_URL

No

https://app.betacit.com

API base URL (for self-hosted deployments)

TACIT_OAUTH_ISSUER

No

OAuth issuer URL (enables OAuth 2.1 mode)

PORT

No

3001

HTTP server port

HOST

No

0.0.0.0

HTTP server bind address

MCP_PATH

No

/mcp

HTTP MCP endpoint path

Development

npm run dev       # watch mode — stdio transport
npm run dev:http  # watch mode — HTTP transport
npm run build     # compile TypeScript
npm start         # run stdio transport
npm run start:http # run HTTP transport

License

MIT

Available Tools

4 tools
tacit_graphqlQuery Building Data (GraphQL)A
Read-onlyIdempotent

Execute a GraphQL query against the Tacit building digital twin API.

Compose any query using the Brick-compliant schema. Supports nested fields, filtering by Brick class, supply chain traversal (upstream/downstream), and recursive location hierarchy.

Use tacit_list_sites first to get a valid site ID, then construct queries freely.

Args:

  • site_id (string, required): The site ID (injected as siteId into your query variables)

  • query (string, required): GraphQL query string

  • variables (string, optional): JSON-encoded variables object (siteId is auto-injected)

Tacit GraphQL Schema - Brick-compliant Building API

Root Queries

All root queries require siteId (get from tacit_list_sites).

building(siteId!, id, name, nameMatch) → [Building] equipment(siteId!, id, name, nameMatch, locationId, locationName, systemId, is, hasProperty, propertyValue) → [Equipment] point(siteId!, id, name, nameMatch, equipmentId, locationId, locationName, zoneId, systemId, is, equipmentIs, hasProperty, propertyValue) → [Point] zone(siteId!, id, name, nameMatch, locationId, is, hasProperty, propertyValue) → [Zone] system(siteId!, name, nameMatch, is, hasProperty, propertyValue) → [System] location(siteId!, locationId!) → Location entityByIfcId(siteId!, ifcId!) → KgEntity (union: Building | Location | Zone | System | Equipment)

Types and Fields

Building { uri, id, name, type, ifcId, properties { name value unit } locations(name, nameMatch, is, recursive) → [Location] zones(name, nameMatch, is, recursive) → [Zone] systems(name, nameMatch, is, recursive) → [System] equipment(name, nameMatch, is, recursive) → [Equipment] points(name, nameMatch, is, recursive) → [Point] }

Equipment { uri, id, name, type, typeHierarchy, ifcId, properties { name value unit } points(name, nameMatch, is) → [Point] # sensors/actuators on this equipment parts(name, nameMatch, is) → [Equipment] # sub-components partOf → Equipment # parent equipment feeds(name, nameMatch, is) → [Equipment] # what this equipment feeds fedBy(name, nameMatch, is) → [Equipment] # what feeds this equipment upstream(maxDepth, medium, is) → [Equipment] # full upstream chain downstream(maxDepth, medium, is) → [Equipment] # full downstream chain location → Location systems → [System] }

Point { uri, id, name, type, typeHierarchy, unit, equipmentId, timeseriesId currentValue { value timestamp quality } # latest live reading (null if no data) properties { name value unit } equipment → Equipment location → Location }

Zone { uri, id, name, type, typeHierarchy, ifcId, properties { name value unit } points(name, nameMatch, is) → [Point] fedBy(name, nameMatch, is) → [Equipment] # equipment feeding this zone upstream(maxDepth, medium, is) → [Equipment] locations → [Location] }

System { uri, id, name, type, ifcId, properties { name value unit } equipment(name, nameMatch, is, recursive) → [Equipment] points(name, nameMatch, is, recursive) → [Point] }

Location { uri, id, name, type, ifcId, properties { name value unit } locations(name, nameMatch, is, recursive) → [Location] # child locations parent → Location equipment(name, nameMatch, is, recursive) → [Equipment] points(name, nameMatch, is, recursive) → [Point] zones → [Zone] }

Enums

NameMatch: CONTAINS | EXACT (default: CONTAINS)

Filter Parameter Guide

  • "is" filters by Brick class: "AHU", "VAV", "FCU", "Temperature_Sensor", "HVAC_Zone", etc.

  • "recursive: true" traverses the full hierarchy (e.g. all equipment in a building, not just direct children)

  • "nameMatch: EXACT" for exact name match, CONTAINS for partial

  • "upstream/downstream" traces the feeds/fedBy supply chain (use maxDepth to limit)

  • "medium" on upstream/downstream filters by medium type (e.g. "HOT_WATER", "CHILLED_WATER", "AIR")

  • "hasProperty" + "propertyValue" filter entities by custom properties

  • "equipmentIs" on points filters by the Brick class of the parent equipment

Example Queries

List AHUs with their sensor points

{ equipment(siteId: "x", is: "AHU") { name type points { name type unit timeseriesId } } }

Trace what feeds a zone

{ zone(siteId: "x", name: "Atrium") { name upstream(maxDepth: 3) { name type } } }

Building floor hierarchy with equipment

{ building(siteId: "x") { name locations(recursive: true) { name type equipment { name type } } } }

Equipment detail with parts and supply chain

{ equipment(siteId: "x", name: "AHU-001") { name type parts { name type } feeds { name type } fedBy { name type } points { name type unit timeseriesId } } }

All temperature sensors with current values

{ point(siteId: "x", is: "Temperature_Sensor") { name unit timeseriesId currentValue { value timestamp } equipment { name type } location { name } } }

Points on VAVs in a specific location

{ point(siteId: "x", locationName: "Tower West", equipmentIs: "VAV") { name type unit timeseriesId equipment { name } } }

Look up an entity by its IFC Global ID

{ entityByIfcId(siteId: "x", ifcId: "3Zu5Bv0LOHrPC6") { ... on Equipment { name type points { name } } ... on Location { name type } } }

Inputs: site_id (required), query (required), variables.

tacit_list_filesList Site FilesA
Read-onlyIdempotent

List documents and files associated with a site.

Returns metadata for files uploaded to a site: spec sheets, maintenance documents, BIM source files, 3D models, and knowledge graph data.

Useful for answering questions like "What documentation exists for this building?" or "Are there spec sheets for this equipment?"

Args:

  • site_id (string, required): The site ID (from tacit_list_sites)

  • category (string, optional): Filter by file type. One of: kg-csv, model-3d, bim-source, spec-sheet, maintenance, other

  • entity_uri (string, optional): Filter by associated entity URI (from GraphQL entity.uri field)

Returns: List of files with name, category, size, and upload date.

Inputs: site_id (required), category, entity_uri.

tacit_list_sitesList SitesA
Read-onlyIdempotent

List all building sites the current API key has access to.

Each site represents a physical location (building, campus, warehouse) managed in Tacit. Sites are the top-level container. You need a site ID to query buildings, equipment, points, zones, and systems.

Returns: Array of sites with id, name, address, city, country, timezone.

Use this tool first to discover available sites before querying building data.

Inputs: no named parameters.

tacit_timeseriesQuery Time-Series DataA
Read-onlyIdempotent

Query historical or live sensor data for one or more points.

Points are identified by their timeseriesId (UUID). Use tacit_graphql first to find points and their timeseriesId values.

Args:

  • site_id (string, required): The site ID

  • point_ids (string, required): Comma-separated timeseriesId UUIDs (max 200)

  • start (string, optional): Start time, relative like "-1h", "-24h", "-7d" or ISO 8601. Default: "-1h"

  • end (string, optional): End time, "now()" or ISO 8601. Default: "now()"

  • window (string, optional): Aggregation window like "5m", "1h", "1d". Only with aggregate.

  • aggregate (string, optional): Aggregation function: mean, min, max, sum, count, first, last. Default: "mean"

  • limit (number, optional): Max records per point (1-10000). Default: 1000

Common patterns:

  • Last hour raw: start="-1h" (default)

  • Daily averages for a week: start="-7d", window="1d", aggregate="mean"

  • Last 24h at 15-min intervals: start="-24h", window="15m"

For current/live values, use tacit_graphql with the currentValue { value timestamp quality } field on Point instead of this tool.

Returns: Array of series, each with timeseriesId, name, type, unit, equipment, and data records [{t, v}].

Inputs: site_id (required), point_ids (required), start, end, +3 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.4/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a distinct and non-overlapping purpose: tacit_list_sites lists sites, tacit_graphql queries building data, tacit_timeseries retrieves sensor data, and tacit_list_files lists documents. The descriptions clearly differentiate their functions, with no ambiguity in tool selection.

    Naming Consistency5/5

    All tool names follow a consistent 'tactic_' prefix with descriptive snake_case suffixes (e.g., tacit_list_sites, tacit_graphql). This pattern is uniform across all four tools, making them predictable and easy to identify.

    Tool Count5/5

    With 4 tools, the server is well-scoped for its purpose of interacting with building digital twin data. Each tool serves a critical role: site discovery, data querying, timeseries retrieval, and file listing, providing a complete workflow without unnecessary complexity.

    Completeness4/5

    The tool set covers core operations for building data access: listing sites, querying entities, retrieving timeseries, and listing files. Minor gaps exist, such as no explicit tools for creating or updating data, but the GraphQL tool allows flexible queries that can handle many needs, making it reasonably complete for query-focused workflows.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Connects AI assistants to SkySpark and Haxall building automation systems by dynamically exposing SkySpark Axon functions as MCP tools. Enables natural language interaction with building data, equipment, and automation functions through real-time tool discovery.
      5
      MIT
    • A
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables AI assistants to interact with SkyFoundry SkySpark building automation data via the Model Context Protocol. It allows users to evaluate Axon expressions, perform CRUD operations on records, and manage project functions through a comprehensive suite of 21 tools.
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      Enables AI assistants to interact with the aedifion cloud platform for building performance optimization and IoT data management. It provides over 95 tools for monitoring timeseries data, managing project components, and executing building analytics or controls.
      100
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI assistants to create, edit, and simulate EnergyPlus building energy models via natural language. Supports schema exploration, model editing, simulation execution, and documentation search.
      39
      237 PyPI
      14
      MIT