DataForge Semantic MCP Server

22 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated:

1 can modify or destroy data
21 read-only
22 tools total

Community server · catalogue entry verified 03/07/2026

How to control DataForge Semantic MCP Server ↓

What DataForge Semantic MCP Server exposes to your agents

Read (21) Write / Execute (1) Destructive / Financial (0)
High Risk

The most dangerous DataForge Semantic MCP Server tools

1 of DataForge Semantic MCP Server's 22 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control DataForge Semantic MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and DataForge Semantic MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations
{
  "df_generate_sql": {
    "limits": [
      {
        "counter": "df_generate_sql_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "df_get_connection": {
    "limits": [
      {
        "counter": "df_get_connection_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register DataForge Semantic MCP Server — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON DATAFORGE SEMANTIC →

Instant setup, no code required.

All 22 DataForge Semantic MCP Server tools

READ 21 tools
Read df_get_connection Get connection details. Optionally include database schema. Read df_get_connection_schema Get database schema snapshot for a connection. Read df_get_consolidated_rmd Get consolidated RMD export: project, Read df_get_data_mart Get data mart details including selected measures, Read df_get_data_mart_view Get physical view metadata for a data mart. Read df_get_dimension_group Get dimension group details including dimensions and related fact tables. Read df_get_dimensions Get dimensions for a project version. Read df_get_fact_table Get fact table details including measures, dimensions, Read df_get_facts Get facts for a project version. Read df_get_measures Get measures (metrics) for a project version. Read df_get_relationship Get relationship details between a fact table and a dimension group. Read df_get_rmd Get full RMD (measures + dimensions + facts) for a project version. Read df_health Check DataForge MCP server health, API connectivity and cache status. Read df_list_connections List database connections for a project version. Read df_list_data_marts List data marts for a project version. Read df_list_dimension_groups List dimension groups for a project version. Read df_list_fact_tables List fact tables for a project version. Read df_list_projects List available DataForge projects. Read df_list_relationships List relationships for a project version. Read df_list_versions List versions for a DataForge project. Read df_refresh_cache Force refresh cached RMD data for a project version.

Questions about DataForge Semantic MCP Server

How do I prevent bulk modifications through DataForge Semantic MCP Server? +

The DataForge Semantic MCP Server server has 1 write tools including df_generate_sql. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach DataForge Semantic MCP Server.

How many tools does the DataForge Semantic MCP Server MCP server expose? +

22 tools across 2 categories: Read, Write. 21 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on DataForge Semantic MCP Server? +

Register the DataForge Semantic MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every DataForge Semantic MCP Server tool call.

Deterministic rules across all 22 DataForge Semantic MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

22 DataForge Semantic MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.