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 commands/paiml/rust-mcp-sdk/devgit clone --depth 1 https://github.com/paiml/rust-mcp-sdkWhat 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 | $0.00000 | $0.00374 |
| Opus 5 | $0.00000 | $0.00187 |
| Sonnet 5 | $0.00000 | $0.00075 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
dev 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 2d 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.
What it actually says
cargo pmcp dev
Start a development server.
Usage
cargo pmcp dev --server <NAME> [OPTIONS]
Description
Builds and runs an MCP server with HTTP transport for local development. The server starts on http://0.0.0.0:<port> with live logs in the terminal.
If the server has a configured port in the workspace config, that port is used automatically (unless overridden with --port).
Options
| Option | Default | Description |
|---|---|---|
--server <NAME> |
(required) | Name of the server to run |
--port <PORT> |
3000 |
Port to run the server on (overrides workspace config) |
--connect <CLIENT> |
- | Automatically connect to an MCP client (claude-code, cursor, inspector) |
Examples
Start a server:
cargo pmcp dev --server calculator
Start on a custom port:
cargo pmcp dev --server calculator --port 8080
Start and connect to Claude Code in one step:
cargo pmcp dev --server calculator --connect claude-code
What It Does
- Builds the server binary (
cargo build --bin {name}-server) - Optionally runs
connectto register with an MCP client - Starts the server in the foreground with
MCP_HTTP_PORTandRUST_LOG=info
Press Ctrl+C to stop the server.
Related Commands
cargo pmcp connect- Connect to a client separatelycargo pmcp test- Run tests against the running server
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.
- 2d ago First seen · 54 lines · 0 tokens per session scan A 15724ac6a2f7
dev is a command published in the GitHub repository paiml/rust-mcp-sdk (53 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 374 tokens. 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.
Other commands, from other repositories
build-agent
Build an AI agent on Cloudflare using the Agents SDK.
openhands-cloud
Unified OpenHands plugin — bundles the OpenHands Cloud CLI, Cloud REST API (openhands-api), Automations (openhands-automation), and Software Agent SDK reference (openhands-sdk) into a single plugin. Use this when you need to interact with OpenHands Cloud or build agents with the SDK.
galileo-agent-control-setup
Render, validate, and optionally apply Agent Control server/auth/control/runtime/sink assets plus Splunk Platform and Splunk Observability handoffs.
huaweicloud-doctor
Self-check Huawei Cloud DevKit readiness — hcloud, MCP, skills, auth.
estate-army-deploy
Production deploy / scale / Standing phase harness for a sovereign intelligence estate. Activates always-on Steward runtime, health loops, self-healing, attestation gates, cost plane hooks, and dashboard entry. Companion to estate-blueprint + estate-steward. Completes the Estate Factory commissioning (R4 + evolutions…
orchestrate
Design multi-agent orchestration pattern for OCI.