Borrowing it
Nothing to install: this file belongs to AtlaSent-Systems-Inc/atlasent-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/AtlaSent-Systems-Inc/atlasent-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/AtlaSent-Systems-Inc/atlasent-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/instructions/atlasent-systems-inc/atlasent-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/atlasent-systems-inc/atlasent-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/atlasent-systems-inc/atlasent-mcp-server/claude-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/atlasent-systems-inc/atlasent-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/atlasent-systems-inc/atlasent-mcp-server/claude-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 | $0.03897 | $0.03897 |
| Opus 5 | $0.01948 | $0.01948 |
| Sonnet 5 | $0.00779 | $0.00779 |
| Haiku 4.5 | $0.00390 | $0.00390 |
Grade A, and why
atlasent-mcp-server CLAUDE.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 2d 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.
@atlasent/mcp-server
MCP server that enforces authorize-before-execute for any MCP-compatible AI agent.
Architecture baseline
Canonical cross-repo reference:
atlasent-docs/architecture/ARCHITECTURE-BASELINE.md
This repo's role: MCP distribution layer — exposes AtlaSent authorization as MCP tools (atlasent_evaluate, atlasent_verify_permit) for any MCP-compatible agent host (Claude Desktop, Cursor, Windsurf) without requiring a custom SDK integration.
Cross-repo invariants for this repo:
- Wire shape source of truth:
atlasent-api/supabase/functions/v1-{evaluate,verify-permit}/handler.ts. Do not invent new request/response shapes here. - Fail-closed at every layer: any error in
authorize()orverify()collapses to deny. This is non-negotiable. - 10-second request timeout on every hosted-API fetch (
AbortSignal.timeout()). A hung API must not block the agent. - Mode dispatch reads env vars at call time (not module load), so tests can swap config without reload.
Architecture
src/
decision.ts Decision / VerifyResult types + toolResult() MCP envelope helper
localEngine.ts Tiny rules engine used when no hosted backend is configured
engine.ts authorize() / verify(): dispatches to local or remote; fail-closed wrapper
server.ts createServer(): registers evaluate, verify_permit, deploy_service + 20+ tools
canonCatalog.ts GENERATED-DERIVED: the canonical action specs incl. canon_id (from the atlasent repo); backs atlasent_lookup_action. Re-sync with scripts/sync-canon.mjs
canonGraph.ts GENERATED-DERIVED: per-action knowledge-graph neighborhood + compliance (from atlasent/generated/authorization-graph.json); enriches atlasent_lookup_action. Re-sync with scripts/sync-canon.mjs
atlasCatalog.ts GENERATED-DERIVED: the Knowledge Atlas (concepts + edges, from atlasent-docs/architecture/traceability/atlas.json); backs atlasent_atlas_lookup. Re-vendor with scripts/vendor-atlas.mjs
v2Tools.ts Wave B tools: atlasent_evaluate_many, atlasent_evaluate_stream, atlasent_query
v2Client.ts HTTP clients for Wave A endpoints; FeatureNotEnabledError on 404
complianceTools.ts SCIM, SIEM config, evidence export MCP tools
vqpTools.ts VQP snapshot generation, verification, drift event tools
streamableHttp.ts Streamable HTTP transport (MCP HTTP mode)
index.ts CLI entry point; connects stdio transport
server.test.ts Unit tests: tools/list, evaluate (local + remote), verify_permit, deploy_service
server.readonly.test.ts READONLY mode tests
complianceTools.test.ts Compliance tool unit tests
v2Tools.test.ts V2 Wave B tool unit tests
v2Client.test.ts V2 HTTP client unit tests
streamableHttp.integration.test.ts Streamable HTTP transport integration tests
integration.test.ts Live-API tests; require ATLASENT_API_KEY + ATLASENT_BASE_URL, skip otherwise
integration.write.test.ts Live-API write tests (mutating tools)
examples/
demo.mjs End-to-end script: spawns server, drives evaluate -> deploy -> verify flow
.github/workflows/
ci.yml build + test on push/PR, Node 18/20/22 matrix
integration.yml nightly integration tests against the hosted API
publish.yml npm publish --access public (cosign-signed tarball) on v* tag push, gated by an AtlaSent release check
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.
- 2d ago Changed · +2 lines · +348 tokens per session 211b3236a509
- 3d ago Changed · -2 lines · -29 tokens per session 8969993def3f
- 4d ago Changed · +2 lines · +269 tokens per session 134510eda504
- 10d ago First seen · 165 lines · 3,309 tokens per session scan A d7d9996d9db7
atlasent-mcp-server CLAUDE.md is an instructions file published in the GitHub repository AtlaSent-Systems-Inc/atlasent-mcp-server (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 3,897 tokens to every session, about $0.0195 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
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.
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.
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).