// SCAN REPORT

Sflight

19 tools. 4 can modify or destroy data without limits.

4 write tools that can modify data. Rate limits recommended.

Last updated: 30 Jun 2026

4 can modify or destroy data

15 read-only

19 tools total

Community server · catalogue entry verified 30/06/2026

How to control Sflight ↓

TOOL MAP

What Sflight exposes to your agents

Read (15) Write / Execute (4) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Sflight tools

Execute · High cap_build This tool triggers a CDS (Core Data Services) build process that compiles models into deployment-ready artifacts. Execute · Medium cap_compile Compilation is an Execute-class action because it runs a code generation/transformation process on data. Execute · High cap_cql_query This tool executes arbitrary SQL queries against a database. Execute · High cap_query The tool executes queries against a live CAP service.

4 of Sflight's 19 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Sflight

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

Cap read operations

{
  "cap_associations": {
    "limits": [
      {
        "counter": "cap_associations_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

Create a free account and register Sflight — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON SFLIGHT →

Instant setup, no code required.

FULL CATALOGUE

All 19 Sflight tools

EXECUTE 4 tools

Execute cap_build Run CDS build (production or development). Compiles CDS models to deployment artifacts Execute cap_compile Compile CDS model to various output formats: json (CSN), edm/edmx (OData metadata), Execute cap_cql_query Execute a SQL query against the CAP project database (in-memory SQLite with all CSV seed data loaded). Execute cap_query Execute a CQL or OData-style query against the running CAP service.

READ 15 tools

Read cap_associations List all associations and compositions across the entire CDS model or for a specific entity. Read cap_csv_inspect Inspect CSV seed data files in the db/data/ directory. Lists available CSV files, Read cap_data_distribution Analyze data distribution by grouping any entity column and counting rows. Read cap_data_stats Get row counts for all entities in the CAP project database. Shows which tables have data Read cap_db_schema List all database tables with column definitions (name, type, key status) AND relationship info Read cap_edm Generate OData V4 EDMX metadata for the service. Shows all EntitySets, NavigationPropertyBindings, Read cap_entities List all CDS entities in the CAP project with their key fields, element count, and association/composition cou Read cap_entity_detail Get the full definition of a specific CDS entity including all fields with types, Read cap_hana_mapping Show the mapping between CDS entities and their generated HANA artifacts (hdbtable/hdbview names). Read cap_mta_info Parse and display the MTA deployment descriptor (mta.yaml). Shows modules, resources, Read cap_nav_map Returns the complete navigation graph of the CDS data model with SQL JOIN conditions. Read cap_project_info Get comprehensive CAP project information: package.json metadata, CDS configuration, Read cap_sample_data Preview sample rows from any entity in the database. Shows column names and actual data values. Read cap_services List all CDS service definitions with their paths, entity counts, and function/action counts. Read cap_yoy_growth Calculate year-over-year growth for any entity. Shows count per year and % change from previous year.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Sflight

Is the Sflight MCP server safe to use without restrictions? +

The Sflight server is primarily read-only with 15 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Sflight MCP server expose? +

19 tools across 2 categories: Execute, Read. 15 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Sflight? +

Register the Sflight 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 Sflight tool call.

Deterministic rules across all 19 Sflight tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SFLIGHT →

Instant setup, no code required.

19 Sflight tools catalogued and risk-classified — across an index of 43,000+ MCP servers.