Borrowing it
Nothing to install: this file belongs to Xerrion/servicenow-platform-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/Xerrion/servicenow-platform-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Xerrion/servicenow-platform-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/xerrion/servicenow-platform-mcp/agents-md)<a href="https://agentmods.dev/instructions/xerrion/servicenow-platform-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/xerrion/servicenow-platform-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/xerrion/servicenow-platform-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/xerrion/servicenow-platform-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 | $0.00748 | $0.00748 |
| Opus 5.5 | $0.00299 | $0.00299 |
| Sonnet 5.5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
servicenow-platform-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 11d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide
This repository provides a Python MCP server for ServiceNow. The installed
entry point is servicenow_mcp.server:main. Python 3.14 is the minimum
supported version; the local mise configuration selects Python 3.15.
Start here
- Check the branch and working tree before editing. Preserve changes made by
others. Work on a feature branch, not
mainormaster. - Trace the affected behavior through the code and tests before changing it. Keep the change focused and update documentation when behavior changes.
- Use
docs/wiki/Development.mdfor the development workflow anddocs/wiki/Architecture.mdfor the module boundaries. - For ServiceNow documentation needed during a review, use
docs/ServiceNowDocs/. The localopenapi-specs/directory contains ServiceNow REST API specifications. Check their scope and version before relying on them.
Implementation boundaries
- Put operation validation, orchestration, and result assembly in
src/servicenow_mcp/capabilities/. MCP adapters belong insrc/servicenow_mcp/mcp/tools/; REST clients and shared metadata belong insrc/servicenow_mcp/platform/. See the development guide before adding a capability or tool. - When changing an MCP tool contract, check its inputs, outputs, annotations,
and
tests/fixtures/native_tool_schemas.json. Exercise the registered tool through the MCP dispatcher when its wire behavior matters.mise run schemasregenerates the fixture; review the resulting diff. - For write workflows, preserve the preview and apply safeguards. A preview must make no upstream write, and an apply token must permit at most one change request. Test relevant failure and stale-state paths.
- Keep credentials, authorization data, and personal data out of source, fixtures, and logs. Treat live instance data as sensitive.
Checks
Run commands from the repository root. Use the existing environment; ask before installing tools or syncing dependencies.
- Markdown changes: run
mise run check:markdownand check affected links and examples. - Python changes: run
mise run lint:pythonandmise run typecheck:python. - Behavior changes: run focused tests, then
UV_NO_SYNC=1 mise run testfor the offline suite. - Cross-stack changes: run
mise run checkandUV_NO_SYNC=1 mise run test.
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.
- 11d ago Changed · +65 lines · +703 tokens per session 3932d25ae09f
- 1mo ago Changed · +1 lines · +15 tokens per session 3fbddd640f11
- 1mo ago Changed · -530 lines · -7,348 tokens per session 4939f0c165a5
- 1mo ago Changed · +19 lines · +334 tokens per session 011a08a6a019
- 1mo ago Changed · -10 lines · -27 tokens per session ab2772aadb22
- 2mo ago Changed · -33 tokens per session 9d25d45cc464
- 2mo ago Changed · +41 lines · +970 tokens per session a45c65ea0992
- 2mo ago First seen · 482 lines · 6,134 tokens per session scan A e8dc48273328
servicenow-platform-mcp AGENTS.md is an instructions file published in the GitHub repository Xerrion/servicenow-platform-mcp (4 stars, last pushed yesterday), licensed MIT. It adds 748 tokens to every session, about $0.0030 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.
servicenow-platform-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| servicenow-platform-mcp AGENTS.mdXerrion/servicenow-platform-mcp | Instructions file | 4 | yesterday | MIT | A | 748 | Codex, OpenCode |
| graftcode graftcode-python.instructions.mdgrft-dev/graftcode | Instructions file | 988 | 1mo ago | none | A | 4,639 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |