agentmods.dev

mcp-for-splunk: Instructions file for Codex

AGENTS.md

mcp-for-splunk AGENTS.md is an instructions file for Codex, OpenCode from deslicer/mcp-for-splunk. It costs 1,314 tokens per session, scanned A, original, Apache-2.0.

A repository guide for AI agents working on an MCP server for Splunk, a platform for searching and monitoring machine-generated data. It covers the server, an optional ITSI extension, setup, checks and project conventions.

In plain words
What is it for?
Use it when developing Splunk or ITSI tools, resources and prompts, or when running the project’s checks and local server.
Why use it?
It gives agents the commands and structure needed to change, test and run the server without overlooking its separate packages or documentation rules.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

This is deslicer/mcp-for-splunk's own configuration. It tells Codex and OpenCode how to work on mcp-for-splunk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-for-splunk configures →

not rated 27repo changed today A scan 1,314 tokens original Apache-2.0
View source ↗ deslicer/mcp-for-splunk
Reuse

Borrowing it

Nothing to install: this file belongs to deslicer/mcp-for-splunk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/deslicer/mcp-for-splunk/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/deslicer/mcp-for-splunk

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for mcp-for-splunk AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/deslicer/mcp-for-splunk/agents-md/github.svg)](https://agentmods.dev/instructions/deslicer/mcp-for-splunk/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/deslicer/mcp-for-splunk/agents-md"><img src="https://agentmods.dev/badge/instructions/deslicer/mcp-for-splunk/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.

agentmods 80×15 button for mcp-for-splunk AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/deslicer/mcp-for-splunk/agents-md"><img src="https://agentmods.dev/badge/instructions/deslicer/mcp-for-splunk/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,314 This file is loaded in full into every session.
When invoked 1,314 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01314 $0.01314
Opus 5.5 $0.00526 $0.00526
Sonnet 5.5 $0.00263 $0.00263
Haiku 4.5 $0.00131 $0.00131

Measured today against content hash b06c7f698903, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-for-splunk 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 today.

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.

AGENTS.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — coding agents in this repo

Instructions for AI coding agents (Cursor, Codex, Copilot, Claude Code, etc.) working in this repository. For agents that only call the running MCP server, prefer llms.txt and mcp_itsi/llms.txt.

Project overview

  • Product: MCP Server for Splunk — FastMCP 4 / MCP SDK v2 tools, resources, and prompts over Splunk Enterprise/Cloud (+ optional ITSI plugin).
  • Runtime pin: fastmcp==4.1.0 (see pyproject.toml / uv.lock; keep fastmcp-slim on the same release via constraint-dependencies).
  • Layout:
    • src/ — core server, tools, resources, middleware
    • mcp_itsi/ — ITSI plugin package (also packaged under packaging/mcp-itsi-server)
    • contrib/ — community tools/workflows
    • scripts/ — live probes and operator helpers
    • docs/ — human docs; follow docs/readme-guide.md when editing Markdown
    • tests/ — pytest suite

Setup

cp env.example .env   # fill Splunk host + token or user/password
uv sync --extra dev

Useful entry points:

uv run mcp-server --local          # local HTTP defaults (sessionless)
uv run python src/mcp_server_for_splunk/server.py --host 127.0.0.1 --port 8014

Build / lint / test

uv run ruff check src/ tests/
uv run mypy src/mcp_server_for_splunk/core/client_config_cache.py   # targeted; full mypy via CI lint job
uv run pytest tests/ -q --ignore=tests/integration

Live Splunk (credentials via env, never commit secrets):

uv run python scripts/test_live_splunk_tools.py
uv run python scripts/test_live_mcp_client.py          # in-memory FastMCP Client
uv run python scripts/test_sessionless_http.py         # needs MCP_URL + SPLUNK_TOKEN

Always regenerate the lockfile when changing deps:

uv lock
uv lock --check

Dependabot PRs that only edit pyproject.toml floors without uv.lock are incomplete.

Conventions

  • Python: 3.11+; keep modules focused; prefer composition over large god-files.
  • File size: stay under ~500 lines; split earlier around ~400.
  • Imports: top of module only (no inline imports unless a documented cycle).
  • Markdown: follow .cursorrules / docs/readme-guide.md (one H1, short paragraphs, fenced code with language tags).
  • HTTP client modes: sessionless is the default (MCP_STATELESS_HTTP=true). See docs/guides/configuration/http-client-modes.md.
  • Workflows: OpenAI Agents workflow_runner was removed (Option C). Keep JSON discovery/authoring tools only (list_workflows, workflow_builder, workflow_requirements).
  • Saved-search ACL: read ownership from entity.access via src/mcp_server_for_splunk/tools/search/saved_search_acl.py — not content['eai:acl'].
  • ITSI packaging: mcp_itsi/ and packaging/mcp-itsi-server/mcp_itsi/ may be hardlinked — edit once, verify both paths if unsure.

Read the full file on GitHub · 126 lines

Changes

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.

  1. today Changed · +42 tokens per session b06c7f698903
  2. 5d ago Changed 3f92b53df685
  3. 21d ago Changed · +18 tokens per session c8a542929ba5
  4. 1mo ago Changed · -2 tokens per session a3393c1671ce
  5. 1mo ago Changed 2df9770ce6b1
  6. 2mo ago First seen · 126 lines · 1,256 tokens per session scan A 157d610ef845

Subscribe to this mod's changes

mcp-for-splunk AGENTS.md is an instructions file published in the GitHub repository deslicer/mcp-for-splunk (27 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,314 tokens to every session, about $0.0053 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 2026-08-30.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens