A command that starts basemind as an MCP server using standard input and output for JSON messages. An MCP server lets an AI client discover and call tools.

Use it with an MCP client or REPL to test JSON-RPC requests, list tools, and inspect tool schemas; automated integrations should use the configured MCP entry.

It provides a direct way to manually test the server and inspect its available tools and input schemas.

serve — Command for Claude Code by Goldziher/basemind

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/Goldziher/basemind

agentmods

npx agentmods add commands/goldziher/basemind/serve

Made for: Claude Code.

Or install basemind, the plugin that ships this one along with the rest of its 15 skills, 11 commands, 2 hooks.

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/commands/goldziher/basemind/serve/github.svg)](https://agentmods.dev/commands/goldziher/basemind/serve)

Your own site

<a href="https://agentmods.dev/commands/goldziher/basemind/serve"><img src="https://agentmods.dev/badge/commands/goldziher/basemind/serve/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/commands/goldziher/basemind/serve"><img src="https://agentmods.dev/badge/commands/goldziher/basemind/serve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 206 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00009	$0.00206
Opus 5.5	$0.00004	$0.00082
Sonnet 5.5	$0.00002	$0.00041
Haiku 4.5	$0.00001	$0.00021

Measured 1mo ago against content hash d1082a7a7011, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

serve 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 1mo 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.

.ai-rulez/commands/serve.md · 27 lines

What it actually says

Serve

Start the basemind MCP stdio server. Useful when manually testing tools via a client like mcp-cli or the rmcp REPL.

Build if stale: cargo build --release.
Run:
```
./target/release/basemind serve
```
The server reads MCP JSON-RPC over stdin and writes responses to stdout. Tool list available via tools/list; per-tool schemas via tools/list + the schema field.

For automated AI-tool integration, prefer the basemind entry in .mcp.json — ai-rulez generate writes it from the [[mcp_servers]] block in .ai-rulez/config.toml.

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.

1mo ago Changed · +6 lines d1082a7a7011
2mo ago First seen · 21 lines · 9 tokens per session scan A 3aa25bdf3db5

Subscribe to this mod's changes

serve is a command published in the GitHub repository Goldziher/basemind (119 stars, last pushed 6d ago), licensed MIT. It adds 9 tokens to every session and 206 once invoked, about $0.0000 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.

RAG and vectors agent-context code-intelligence code-map lancedb mcp

serve next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
serveGoldziher/basemind	Command	119	6d ago	MIT	A	9	Claude Code
reindexrepowise-dev/repowise	Command	8.1k	today	AGPL-3.0	A	26	Claude Code
indexZhuBit/cowork-semantic-search	Command	31	7mo ago	AGPL-3.0	A	10	Claude Code
ingestGalbaz1/video-research-mcp	Command	23	13d ago	MIT	A	10	Claude Code
agentget-convex/convex-agent-plugins	Command	117	1mo ago	MIT	A	21	Claude Code, Cursor
codesage-reindexiliaal/codesage	Command	21	today	MIT	A	28	Claude Code
requirement-reviewxiaozhi86/qamaster	Command	6	2mo ago	MIT	A	53	Claude Code