least-privilege

DE//AGENT currently lists 3 resources under least-privilege: 2 tutorials, 1 skill. Everything below is derived from the live registry — counts, capabilities, verification state and security posture come from the curated records, never from marketing copy.

Documented learning objectives across these resources:

• Read a tool schema and predict its side effects — via MCP Tool Contract Auditor
• Classify tools by blast radius — via MCP Tool Contract Auditor
• Write a least-privilege MCP configuration — via MCP Tool Contract Auditor
• Treat fetched content as untrusted model input and scope its network path — via Production gotchas — untrusted content, destructive actions, permission scope
• Bound destructive actions with deny-by-default hooks — via Production gotchas — untrusted content, destructive actions, permission scope
• Scope every credential to the role and repositories the task needs — via Production gotchas — untrusted content, destructive actions, permission scope

These resources map to stage: Agentic Data Engineering (3). Follow the four-phase roadmap to place this topic inside a progression instead of learning it in isolation.

Every entry, its shape and its trust state — sorted by the registry's composite score. This table is the honest version of a marketing comparison: no sponsored placements, no unverifiable claims.

How scores are computed: source quality score.

Highest composite score first:

1. MCP Tool Contract Auditor score 40.5 — advanced
2. Audit an MCP server's tool contracts score 34.15 — intermediate
3. Production gotchas — untrusted content, destructive actions, permission scope score 34.15 — advanced

Scores rank provenance, completeness and trust — read how verification works before adopting anything.

Reach for these with production experience: MCP Tool Contract Auditor, Production gotchas — untrusted content, destructive actions, permission scope.

Security-flagged entries: MCP Tool Contract Auditor (1 flag). Flags mean the record declares capabilities like credential use or write access — read the security posture on each page before connecting.

• MCP Tool Contract Auditor — Inspects an MCP server's tool list and schemas, flags tools that can write, delete, spend money or exfiltrate data, and produces a least-privilege connection recommendation. details
• Audit an MCP server's tool contracts — Before connecting an MCP server, audit its tools for blast radius. Read each tool schema, classify every tool as Read, Write, Destructive, Spend or Exfiltrate, and produce a least-… details
• Production gotchas — untrusted content, destructive actions, permission scope — An agent executes with your credentials, so its context and config are an attack surface. Read the MCP security model, treat fetched content as untrusted input, keep destructive st… details

Real install commands from the registry — read the source before running any of them:

npx de-agent-platform add mcp-tool-contract-auditor

MCP Tool Contract Auditor — review first

Adjacent topics: security (3 shared), tutorial (2 shared), review (2 shared), mcp (2 shared).

Study path: the roadmap places this topic in a progression · the scoring model explains the numbers · the trust rule catalog shows every security check these entries passed through.