Borrowing it
Nothing to install: this file belongs to HieuAnh87/sentry-selfhosted-mcp. 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/HieuAnh87/sentry-selfhosted-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/HieuAnh87/sentry-selfhosted-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/hieuanh87/sentry-selfhosted-mcp/agents-md)<a href="https://agentmods.dev/instructions/hieuanh87/sentry-selfhosted-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hieuanh87/sentry-selfhosted-mcp/agents-md/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/instructions/hieuanh87/sentry-selfhosted-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hieuanh87/sentry-selfhosted-mcp/agents-md.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 | $0.00715 | $0.00715 |
| Opus 5.5 | $0.00286 | $0.00286 |
| Sonnet 5.5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
sentry-selfhosted-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 21d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
selfhosted-sentry-mcp
TypeScript MCP server for self-hosted Sentry triage/debug workflows.
Commands
# Install deps
npm install
# Build TypeScript to ./build and set executable bit
npm run build
# Watch mode during source edits
npm run watch
# Run MCP inspector against built server
npm run inspector
# Test full suite (Node test runner)
npm test
# Test smoke flow only
npm run test:smoke
# Run one test file
node --test test/tools.test.js
# Docker image build
docker build -t selfhosted-sentry-mcp:latest . # not sentry-selfhosted-mcp: that name is an unrelated npm package
Boundaries
- Do not commit real
SENTRY_AUTH_TOKENor real Sentry URLs in docs/examples. - Do not edit
build/**directly; source of truth issrc/**. - Keep MCP tool names and input schemas backward compatible unless explicitly requested.
- Avoid widening output payloads without grep/filter controls (token bloat risk).
Where to look
| Task | Location | Note |
|---|---|---|
| Tool routing/registry | src/server.ts |
TOOLS array + CallToolRequestSchema switch must stay in sync |
| Env validation/startup behavior | src/config.ts |
validation runs on module load; missing env throws immediately |
| Sentry HTTP endpoints | src/api/client.ts |
all endpoint path composition centralized here; list methods return {data, nextCursor, hasMore} (parsed from Sentry's Link header), not a bare array |
| Output filtering/truncation logic | src/helpers/{filter,truncate,grep}.ts |
use helpers before returning large JSON |
| Tool contract expectations | test/tools.test.js |
expected tool list currently fixed at 28 |
| Pagination | src/helpers/pagination.ts, truncatedTextResult in src/tools/issues.ts |
when more results exist, a tool result carries a second text content block {next_cursor, has_more, hint}; content[0] keeps its shape |
Conventions (deviations only)
- ESM imports use explicit
.jsextension in TS source (Node16 module resolution). - Entry point is intentionally thin:
src/index.tsonly imports./server.jsfor compatibility. - Raw API tool warns on large event payloads and supports
grep_pattern; preserve this behavior. - Tool results may have more than one content block: the main payload first, then an optional pagination block. Don't assume
content.length === 1, and don't fold the cursor intocontent[0]. - Bulk issue mutations must carry an
idorqueryselection in the URL;selectorParamsinsrc/api/client.tsrefuses an empty one. Never bypass it — Sentry applies an unselected bulk update to every unresolved issue in the project.
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.
- 21d ago Changed · +3 lines · +203 tokens per session 115057760eaa
- 2mo ago First seen · 66 lines · 512 tokens per session scan A b636a407df43
sentry-selfhosted-mcp AGENTS.md is an instructions file published in the GitHub repository HieuAnh87/sentry-selfhosted-mcp (10 stars, last pushed 18d ago), licensed MIT. It adds 715 tokens to every session, about $0.0029 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 2026-08-31.
sentry-selfhosted-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sentry-selfhosted-mcp AGENTS.mdHieuAnh87/sentry-selfhosted-mcp | Instructions file | 10 | 18d ago | MIT | A | 715 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |