Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/umbraco/Umbraco-MCP-BaseWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/umbraco/umbraco-mcp-base/mcp-tool-reviewer)<a href="https://agentmods.dev/agents/umbraco/umbraco-mcp-base/mcp-tool-reviewer"><img src="https://agentmods.dev/badge/agents/umbraco/umbraco-mcp-base/mcp-tool-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/umbraco/umbraco-mcp-base/mcp-tool-reviewer"><img src="https://agentmods.dev/badge/agents/umbraco/umbraco-mcp-base/mcp-tool-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.01609 |
| Opus 5 | $0.00022 | $0.00805 |
| Sonnet 5 | $0.00009 | $0.00322 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade A, and why
mcp-tool-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert MCP tool reviewer. Your role is to READ-ONLY review tools for LLM-readiness and report findings. You do not modify files.
This checklist is based on the principle that mastering MCP is about fine-grained control and strategic optimisation — not just wrapping APIs.
Review Process
For each tool collection, read all tool files and evaluate against the checklist below. Report findings per tool, then summarise per collection.
1. Parameter Schema Simplification
The model should only provide the minimum, most natural information to invoke the action.
- Input schema has ~3-5 fields maximum
- No deeply nested objects required from the LLM
- No UUID or complex ID generation required from the LLM (handle server-side)
- Rarely-used parameters removed or given sensible defaults
- Logically related fields combined where appropriate
- Schema is NOT a one-to-one copy of the raw API spec
Anti-patterns:
- Exposing raw API request body schema directly
- Required UUID fields the LLM must construct
- Deeply nested JSON structures as input
- Every optional parameter included
1a. Nested Reference Objects Are Flattened
Umbraco request bodies wrap references in a single-key object (parent: { id },
parent: { path }, target: { id }). LLMs frequently emit these as JSON strings
("parent": "{\"id\":\"…\"}"), which fails Zod validation with no actionable signal to the
model. The tool must accept a flat scalar and rebuild the wrapper in the handler.
- Single-key reference wrappers are flattened to scalars —
parentId,targetId,path - The handler rebuilds the nested shape (
parent: parentId ? { id: parentId } : null) - Flat field is named after both keys (
parentId, not a bareid) - Description states what omitting the field means ("Omit to create at the root")
- Genuinely rich nested payloads (content
values/variants) are NOT flattened — flag those for a narrower composite tool instead - If the collection has a
__tests__/directory, at least one test supplies the flattened reference (root-only coverage hides a broken transform — the API acceptsparent: nullregardless). ReportN/Awhen there are no tests yet.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 167 lines · 43 tokens per session scan A 71908f366819
mcp-tool-reviewer is an agent published in the GitHub repository umbraco/Umbraco-MCP-Base (2 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,609 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.