What is local-llm-mcp CLAUDE.md?

Project instructions for local-llm-mcp, an MCP server that sends prompts to a local language model through Ollama and returns answers immediately. They document the code layout, build and test commands, and how to verify the server over standard input and output.

Use them when developing local-llm-mcp, including building it, running tests, understanding its source files and testing its JSON-RPC tool calls.

Contributors need to know how this server differs from a long-running job system and how its limited tests work. The instructions also explain the extra manual check needed for the live model connection.

How jgt87/local-llm-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jgt87/local-llm-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.

Copy the file

curl -O https://raw.githubusercontent.com/jgt87/local-llm-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/jgt87/local-llm-mcp

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jgt87/local-llm-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/jgt87/local-llm-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/jgt87/local-llm-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jgt87/local-llm-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jgt87/local-llm-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jgt87/local-llm-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,560 This file is loaded in full into every session.

When invoked 1,560 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.

Model	Per session	Once invoked
Fable 5.1	$0.01560	$0.01560
Opus 5.5	$0.00624	$0.00624
Sonnet 5.5	$0.00312	$0.00312
Haiku 4.5	$0.00156	$0.00156

Measured 5d ago against content hash 8b2d75aeeb08, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

local-llm-mcp 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.

CLAUDE.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

What this is

An MCP server that answers prompts with a local model through Ollama, synchronously. Claude calls local_ask or local_classify and gets the answer back in the same turn.

This is the deliberate opposite of the sibling codex-offload server. That one exists because Codex jobs take minutes and must not block; this one exists because a local 7B answers in seconds and wrapping that in a job store, disk state and polling would be pure overhead. If a tool here would need to be polled, it belongs in codex-offload instead, not this one.

Commands

npm run build     # tsc -> dist/
npm run watch     # tsc --watch
npm test          # build, then node --test test/*.test.js

Tests run against the compiled dist/, which is why npm test builds first. They cover matchLabel — the label validation — and nothing else. The HTTP path is deliberately uncovered: exercising it needs a live model, so verify it by driving the built server over stdio with a JSON-RPC script (initialize → notifications/initialized → tools/call).

Layout

src/index.ts — MCP server, tool definitions and their descriptions
src/ollama.ts — HTTP client, plus the pure helpers that keep model output honest
src/openrouter.ts — optional hosted backend (OpenRouter chat completions + model catalogue)
src/prompts.ts — the slash commands, defined once and rendered two ways: as MCP prompts (/mcp__local-llm__commit) and as Claude Code command files (/local_commit). They instruct the calling model how to use the tools; each ends in a verification step, because that is the part the local model cannot do
scripts/commands.mjs — writes commands/local_*.md from the built dist/prompts.js; with --install also to ~/.claude/commands/. Those files are generated: edit src/prompts.ts, then npm run commands (or npm run install-commands)

Configuration

env	default	meaning
`LOCAL_LLM_PROVIDER`	`ollama`	backend used when a call gives no `provider` (`ollama` or `openrouter`)
`OLLAMA_HOST`	`http://127.0.0.1:11434`	Ollama endpoint
`LOCAL_LLM_MODEL`	`qwen2.5-coder:7b`	default model tag
`LOCAL_LLM_TIMEOUT_MS`	`120000`	per-request timeout
`OPENROUTER_API_KEY`	—	required for `provider: "openrouter"`; read at server start
`OPENROUTER_MODEL`	`deepseek/deepseek-v4-flash`	default OpenRouter model id
`OPENROUTER_BASE_URL`	`https://openrouter.ai/api/v1`	API base
`OPENROUTER_TIMEOUT_MS`	`60000`	per-request timeout

Read the full file on GitHub · 104 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.

5d ago Changed · +18 lines · +397 tokens per session 8b2d75aeeb08
2mo ago First seen · 86 lines · 1,163 tokens per session scan A 3f67aef1d9e6

Subscribe to this mod's changes

local-llm-mcp CLAUDE.md is an instructions file published in the GitHub repository jgt87/local-llm-mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 1,560 tokens to every session, about $0.0062 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.

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

local-llm-mcp: Instructions file for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

What this is

Commands

Layout

Configuration

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

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

langchain AGENTS.md

vscode copilot-instructions.md

deepseek-harness AGENTS.md