301-tooling-mcp-reference

A reference guide for tools supplied by several MCP servers, including file editing, GitHub, research, memory, time, and model or dataset search.

In plain words
What is it for?
Use it as a lookup when a workflow needs to read or edit files, search code, manage GitHub repositories, research a topic, store knowledge, convert time zones, or find models and datasets. MCP is a standard way for agents to use connected tools.
Why use it?
It helps an agent know which external tool can handle a particular task and what operations that tool supports.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/hamzaamjad/cursor-rules/301-tooling-mcp-reference
Clone the repo
git clone --depth 1 https://github.com/hamzaamjad/cursor-rules
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 260 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00008 $0.00260
Opus 5 $0.00004 $0.00130
Sonnet 5 $0.00002 $0.00052
Haiku 4.5 $0.00001 $0.00026

Measured yesterday against content hash c2315c1a1b35, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

301-tooling-mcp-reference 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 yesterday.

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.

rules/300-integration/301-tooling-mcp-reference.mdc · 44 lines

What it actually says

MCP Tool Reference

Desktop Commander

edit_block: Line-based precise edits
write_file: Full file write/append
read_file: Partial reads with offset
search_code: Regex with context lines
list_directory: File/dir enumeration
get_file_info: Metadata + line counts

GitHub MCP

create_pull_request: PR creation
push_files: Multi-file commits
search_repositories: Query repos
get_issue: Issue details
fork_repository: Fork to account

Perplexity MCP

perplexity_research: Deep research
perplexity_reason: Complex reasoning
perplexity_ask: Quick queries

Other MCP Servers

  • HuggingFace: Model/dataset search, image generation
  • Memory: Knowledge graph operations
  • Sequential Thinking: Multi-step reasoning
  • Time: Timezone conversions
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. yesterday First seen · 44 lines · 8 tokens per session scan A c2315c1a1b35

Subscribe to this mod's changes

301-tooling-mcp-reference is a cursor rule published in the GitHub repository hamzaamjad/cursor-rules (2 stars, last pushed 1y ago), licensed MIT. It adds 8 tokens to every session and 260 once invoked, about $0.0000 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.