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/ketiil/mcp-cmdb/claude-mdgit clone --depth 1 https://github.com/ketiil/mcp-cmdbWrote 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/ketiil/mcp-cmdb/claude-md)<a href="https://agentmods.dev/instructions/ketiil/mcp-cmdb/claude-md"><img src="https://agentmods.dev/badge/instructions/ketiil/mcp-cmdb/claude-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 | $0.02558 | $0.02558 |
| Opus 5 | $0.01279 | $0.01279 |
| Sonnet 5 | $0.00512 | $0.00512 |
| Haiku 4.5 | $0.00256 | $0.00256 |
Grade A, and why
mcp-cmdb 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 5d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ServiceNow CMDB MCP Server
Python MCP server connecting Claude to ServiceNow CMDB via natural language. Uses FastMCP, OAuth 2.0, async httpx, pydantic. Targets ServiceNow Xanadu+.
Tech Stack
- Python 3.11+, FastMCP (
mcp[cli]>= 1.2.0), httpx (async), pydantic + pydantic-settings - Transport: STDIO only
- Auth: OAuth 2.0 password grant against
/oauth_token.do - ServiceNow APIs: Table API, CMDB Instance API, Aggregate API, Data Model Navigator tables
Project Structure
src/servicenow_cmdb_mcp/
├── server.py # FastMCP server setup, entry point + check_connection tool
├── client.py # Async ServiceNow REST client (auth, requests, pagination)
├── config.py # Pydantic settings from env vars (SN_INSTANCE_URL, SN_CLIENT_ID, etc.)
├── cache.py # In-memory metadata cache with TTL
├── redaction.py # Credential pattern scrubbing in script bodies
├── errors.py # Structured error types: ServiceNowError base, PermissionError, RateLimitError, etc.
├── tools/ # One module per domain, each exports register_*_tools(mcp, client[, cache])
│ ├── _utils.py # Shared validators, pagination helpers, JSON serialization
│ ├── queries.py # search_cis, query_cis_raw, get_ci_details, count_cis, suggest_table, list_ci_classes, describe_ci_class
│ ├── relationships.py # get_ci_relationships, get_dependency_tree, get_impact_summary, find_ci_path, list_relationship_types, find_related_cis
│ ├── health.py # find_orphan_cis, find_duplicate_cis, find_stale_cis, cmdb_health_summary
│ ├── mutations.py # preview_ci_update/create → confirm_ci_update/create (two-phase)
│ ├── configurables.py # get_business_rules, get_flows, get_flow_details, get_client_scripts, get_acls, get_script_includes, analyze_configurables
│ ├── discovery.py # list_discovery_schedules, get_discovery_status, get_discovery_errors
│ ├── ire.py # get_identification_rules, get_reconciliation_rules, explain_duplicate
│ ├── imports.py # list_data_sources, get_import_set_runs, get_transform_errors
│ └── _tree_format.py # ASCII tree rendering for dependency tree output
├── resources/schema.py # Dynamic MCP Resources + refresh_metadata_cache tool
└── prompts/workflows.py # MCP Prompts: Health Check, Impact Analysis, Troubleshoot CI, Audit Configurables
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.
- 5d ago First seen · 205 lines · 2,558 tokens per session scan A d9a8cfe21964
mcp-cmdb CLAUDE.md is an instructions file published in the GitHub repository ketiil/mcp-cmdb (0 stars, last pushed 3mo ago), licensed MIT. It adds 2,558 tokens to every session, about $0.0128 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
mcp-server-starrocks CLAUDE.md
Claude Code instructions for StarRocks/mcp-server-starrocks, covering claude.md, project overview, development commands, run the server directly for testing and run with test mode to verify table overview functionality.
serac AGENTS.md
Instructions for serac-labs/serac, covering agents.md, commits and pr titles, style guide, general principles and destructuring.
seekstone CLAUDE.md
Claude Code instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
now-sdk-ext-mcp CLAUDE.md
Instructions for sonisoft-cnanda/now-sdk-ext-mcp, covering now-sdk-ext-mcp, project overview, architecture, directory structure and sibling projects.
now-sdk-ext-mcp AGENTS.md
Instructions for sonisoft-cnanda/now-sdk-ext-mcp, covering agents.md, what this repository is, hard rules, 1. never write to stdout and 3. adding a tool touches two files, and nothing enforces it.
run402 CLAUDE.md
Claude Code instructions for kychee-com/run402, a project described as: Full-stack backend infrastructure for AI agents: Postgres, auth, storage, serverless functions and atomic deploys. TypeScript SDK, CLI and MCP server. Paid with x402/MPP. Open source.