// SCAN REPORT

Adr Skills

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

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

Last updated: 29 Jun 2026

4 can modify or destroy data

5 read-only

9 tools total

Community server · catalogue entry verified 29/06/2026

How to control Adr Skills ↓

TOOL MAP

What Adr Skills exposes to your agents

Read (5) Write / Execute (4) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Adr Skills tools

Write · Medium generate_adr This tool creates new Architecture Decision Records (markdown files) based on session analysis. Write · Medium link_adrs This tool creates or modifies metadata by establishing links between Architecture Decision Records. Write · Medium save_session The tool creates or modifies data in a database (a development session record) in a reversible manner. Write · Medium update_adr_status The tool creates or modifies data reversibly by changing ADR status fields.

4 of Adr Skills's 9 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Adr Skills

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

Rate limit write operations

{
  "generate_adr": {
    "limits": [
      {
        "counter": "generate_adr_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_stale_adrs": {
    "limits": [
      {
        "counter": "check_stale_adrs_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 Adr Skills — 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 ADR SKILLS →

Instant setup, no code required.

FULL CATALOGUE

All 9 Adr Skills tools

WRITE 4 tools

Write generate_adr Analyze a saved session and auto-generate an ADR. Exports a markdown file and warns about similar past decisio Write link_adrs Create a relationship between two ADRs: related_to, conflicts_with, or depends_on Write save_session Save a Claude Code development session to the database Write update_adr_status Update the status of an ADR: Proposed → Accepted → Deprecated → Superseded

READ 5 tools

Read check_stale_adrs Find Accepted ADRs that have not been reviewed in a while and may need revisiting Read get_adr_graph Visualize ADR dependency graph. Optionally scope to a single ADR. Read get_timeline Get the decision timeline for a project Read review_adr AI quality review of an ADR — scores completeness, flags missing context, unconsidered alternatives, and optim Read search_decisions Search past architectural decisions by keyword

FAQ

Questions about Adr Skills

How do I prevent bulk modifications through Adr Skills? +

The Adr Skills server has 4 write tools including generate_adr, link_adrs, save_session. 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 Adr Skills.

How many tools does the Adr Skills MCP server expose? +

9 tools across 2 categories: Read, Write. 5 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Adr Skills? +

Register the Adr Skills 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 Adr Skills tool call.

Deterministic rules across all 9 Adr Skills tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ADR SKILLS →

Instant setup, no code required.

9 Adr Skills tools catalogued and risk-classified — across an index of 43,000+ MCP servers.