// SCAN REPORT

Sfgraph

28 tools. 3 can modify or destroy data without limits.

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

Last updated: 2 Jul 2026

3 can modify or destroy data

25 read-only

28 tools total

Community server · catalogue entry verified 02/07/2026

How to control Sfgraph ↓

TOOL MAP

What Sfgraph exposes to your agents

Read (25) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Sfgraph tools

Execute · Medium start_ingest_job RETURNS INSTRUCTIONS ONLY. The MCP server does NOT run ingest workers. To actually ingest, run Write · High deployment_manifest_gen This tool generates deployment manifest files including destructiveChanges.xml, which defines components to be deleted in a Salesforce deployment. Write · Medium snapshot_create The tool creates a new snapshot (a saved state of the graph), which is a write operation.

3 of Sfgraph's 28 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Sfgraph

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

Rate limit write operations

{
  "deployment_manifest_gen": {
    "limits": [
      {
        "counter": "deployment_manifest_gen_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_field": {
    "limits": [
      {
        "counter": "analyze_field_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 Sfgraph — 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 SFGRAPH →

Instant setup, no code required.

FULL CATALOGUE

All 28 Sfgraph tools

EXECUTE 1 tools

Execute start_ingest_job RETURNS INSTRUCTIONS ONLY. The MCP server does NOT run ingest workers. To actually ingest, run

WRITE 2 tools

Write deployment_manifest_gen Generate package.xml + destructiveChanges.xml from cross-org diff. Write snapshot_create Create a graph snapshot for an org.

READ 25 tools

EXPLORE

Related servers

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

FAQ

Questions about Sfgraph

How do I prevent bulk modifications through Sfgraph? +

The Sfgraph server has 2 write tools including deployment_manifest_gen, snapshot_create. 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 Sfgraph.

How many tools does the Sfgraph MCP server expose? +

28 tools across 3 categories: Execute, Read, Write. 25 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Sfgraph? +

Register the Sfgraph 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 Sfgraph tool call.

Deterministic rules across all 28 Sfgraph tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SFGRAPH →

Instant setup, no code required.

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