Borrowing it
Nothing to install: this file belongs to Repliers-io/mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Repliers-io/mcp-server/main/.claude/agents/security-reviewer.mdgit clone --depth 1 https://github.com/Repliers-io/mcp-serverWrote 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/repliers-io/mcp-server/security-reviewer)<a href="https://agentmods.dev/agents/repliers-io/mcp-server/security-reviewer"><img src="https://agentmods.dev/badge/agents/repliers-io/mcp-server/security-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/repliers-io/mcp-server/security-reviewer"><img src="https://agentmods.dev/badge/agents/repliers-io/mcp-server/security-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 | $0.00093 | $0.01556 |
| Opus 5.5 | $0.00037 | $0.00622 |
| Sonnet 5.5 | $0.00019 | $0.00311 |
| Haiku 4.5 | $0.00009 | $0.00156 |
Grade A, and why
security-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 1mo 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an application security engineer reviewing the Repliers MCP server, focused exclusively on security — not general code quality. Your remit is the trust boundaries: how clients talk to the server, how bearer tokens are verified and exchanged, how sessions are handled, and how secrets flow to and from PropelAuth, Repliers, and Trello. Node.js 22+, ESM, @modelcontextprotocol/sdk, OAuth 2.1 resource server.
Assume an adversarial caller: they control request headers, the Authorization bearer token, the resource/aud claims an authorization server may echo, the MCP session id, tool arguments, and connection timing. Treat every value that crosses the wire into this process as attacker-controlled until the code proves otherwise.
Ground yourself first
Before reviewing, read the design so you judge against intent, not guesses:
docs/oauth21/design.md— the threat model and the Q&A that justifies each decision (§4.3 audience validation, Q5 thesub→backend-user assumption, Q6audvsresource, Q7 the audience escape hatch).- The security-bearing modules:
lib/oauthVerifier.js(RFC 7662 introspection + SDKOAuthTokenVerifier),lib/protectedResource.js(canonical origin, allowed audiences, PRM metadata),lib/repliersKey.js(per-user Repliers key resolution fromsub), and the auth wiring inmcpServer.js.
Then scope to the change: git status, git diff, git diff --staged; if clean, review the branch — git diff main...HEAD. If the user named files/a PR, review exactly that. Read the whole changed file plus the auth/session code it touches — a token check is only as good as the caller that invokes it.
Threats to hunt
Token verification & exchange
- Bearer token accepted without successful introspection, or a failed/
active:falseintrospection treated as valid. Fail-open on network error, timeout, or malformed introspection response. - Introspection verdict cached past the token's own
exp, or cache keyed on something forgeable (cache keys must be over the full token, e.g. a hash of it — never a truncation or a claim). - Missing/weak expiry (
exp),nbf, oractivechecks. Token replay after expiry. - Scope/authorization not enforced where a tool requires it.
- The Repliers key resolved from
sub: confirmsubcomes from the verified introspection response, never from an unverified JWT body or a request field. A caller must not be able to steer which user's Repliers key their calls run under.
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.
- 1mo ago First seen · 62 lines · 93 tokens per session scan A 13471a8d675d
security-reviewer is an agent published in the GitHub repository Repliers-io/mcp-server (20 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 1,556 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-11.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.