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.
npx agentmods add instructions/elad12390/sentry-mcp/agents-mdgit clone --depth 1 https://github.com/elad12390/sentry-mcpWrote 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/instructions/elad12390/sentry-mcp/agents-md)<a href="https://agentmods.dev/instructions/elad12390/sentry-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/elad12390/sentry-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.00661 | $0.00661 |
| Opus 5 | $0.00331 | $0.00331 |
| Sonnet 5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
sentry-mcp AGENTS.md 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 4d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines for Sentry MCP
Build & Test
- Install:
bun install(ornpm install) - Build:
bun run build(compiles TypeScript todist/) - Type check:
bun run typecheck(tsc --noEmit) - Tests:
bun test(vitest; unit tests mock the Sentry client)
Architecture
src/config.ts— env config (SENTRY_AUTH_TOKEN,SENTRY_URL,SENTRY_ORG,SENTRY_PROJECT) via zod.src/lib/sentry-client.ts— axios client for the Sentry REST API (/api/0/...), Bearer auth, org/project auto-resolution, repeated-key param serialization.src/lib/metrics.ts— usage metrics persisted to~/.sentry-mcp-metrics.json.src/tools/*.ts— one file per tool. Register new tools insrc/tools/index.ts(toolsarray +handlersmap).src/prompts/index.ts— guided workflow prompts.src/index.ts— MCP server: registers tools, prompts, and resources (sentry://projects,sentry://tags,sentry://tags/{key}/values).
Code Style
- Imports: use
.jsextensions for local imports (ES modules):import { x } from "./file.js". - Types: TypeScript strict mode. Explicit types for function params.
anyis acceptable for external Sentry/axios shapes, with an inline comment. - Naming: functions camelCase (
handleSearchIssues); classes PascalCase (SentryClient,MetricsManager); instances camelCase (sentryClient,metrics). - Error Handling: tool handlers may throw; the server wraps them and returns
{ content: [{ type: "text", text: "Error: ..." }], isError: true }. The client converts axios errors intoSentry API Error: <status> - <body>with scope/region hints. - Tool Descriptions: MUST include explicit trigger phrases. Format:
"🔍 Use when user asks: 'phrase1', 'phrase2'. What it does."This is critical for AI discoverability. - Console: use
console.error()only (stdout is reserved for the MCP protocol).
Sentry API notes
- Base URL is region-specific for SaaS (
https://us.sentry.io,https://de.sentry.io);https://sentry.iois the default. - Issue search uses the org issues endpoint with Sentry search syntax in
query(is:unresolved,level:error, ...). - Counts/trends use
events-timeseries(dataseterrors,yAxis=count());is:tokens are issue-only and are stripped before querying events. - Tag values are project-scoped; the client resolves a default project when none is given.
- Trace lookup uses
/organizations/{org}/trace/{trace_id}/and flattens the returned span/error tree.
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.
- 4d ago First seen · 31 lines · 661 tokens per session scan A 518b6e866c86
sentry-mcp AGENTS.md is an instructions file published in the GitHub repository elad12390/sentry-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 661 tokens to every session, about $0.0033 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).