New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

MCP Tools

by Consensys in Consensys/c0

A skill your agent uses when adding, changing, or reviewing MCP servers, MCP tools, session tools, tool registration, Cloudflare AI Search sources, AI Search ingestion resources, or the AI Search…

LGPL-3.0Auto-check passedAgent Workflows

Install MCP Tools

skills CLI
$ npx skills add Consensys/c0 --skill mcp-tools -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Consensys/c0 mcp-tools --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Consensys/c0.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/mcp-tools .claude/skills/mcp-tools && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
mcp-tools
GitHub stars
105
Token cost
~1.1k tokens
SKILL.md length
524 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
LGPL-3.0

At a glance

A skill your agent uses when adding, changing, or reviewing MCP servers, MCP tools, session tools, tool registration, Cloudflare AI Search sources, AI Search ingestion resources, or the AI Search…

  • Works in 7 steps: Put user/session-visible identifiers in… → Normalize and validate user-selected… → Register MCP tools with stable,… → …
  • Reviewing MCP servers
  • SKILL.md covers General MCP And Tool Pattern, Internal MCP Rules, AI Search Source Pattern and Runtime-Configured AI Search…, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

MCP Tools is an agent skill from Consensys/c0. Use when adding, changing, or reviewing MCP servers, MCP tools, session tools, tool registration, Cloudflare AI Search sources, AI Search ingestion resources, or the AI Search MCP server in this repo.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol and Cloudflare. The repository describes itself as: c0 is an open-source AI platform built for organizational work, tools, and context. A single deployment to Cloudflare to get started. The licence is LGPL-3.0.

When your agent uses it

  • Reviewing MCP servers
  • Tool registration
  • Cloudflare AI Search sources
  • AI Search ingestion resources

Example prompts

  • “/mcp-tools”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Put user/session-visible identifiers in the shared package first.
  2. Normalize and validate user-selected tools at the boundary where tools enter session state.
  3. Register MCP tools with stable, action-oriented names and descriptions that state what the tool returns.
  4. Keep authorization and selection outside the runtime. The MCP server should only register tools attached to the current session.
  5. Dispatch from the tool registration into a shared runtime function. Do not fork source-specific logic into separate MCP servers unless the…
  6. Preserve isolate behavior. Docs-only sessions must not require an attached repository.
  7. Update tests at the contract, MCP config, runtime, and Worker route levels when the public tool surface changes.

What it can do on your machine

Read from SKILL.md and the folder at commit e7a1810. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

MCP Tools loads about 1.1k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 524 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Consensys/c0 at commit e7a1810, republished under its LGPL-3.0 licence (© Consensys). 524 words, ~1,122 tokens.

Download SKILL.mdSave it as .claude/skills/mcp-tools/SKILL.md (or your agent's skills folder).
name
mcp-tools
description
Use when adding, changing, or reviewing MCP servers, MCP tools, session tools, tool registration, Cloudflare AI Search sources, AI Search ingestion resources, or the AI Search MCP server in this repo.

MCP Tools

Use this skill when working on MCP/tool behavior in this repo. Start from the shared contracts and existing registration points, then wire the runtime. Avoid adding one-off tool code when an existing tool surface or registry can express the behavior.

General MCP And Tool Pattern

  • Shared session tool contracts live in packages/shared/src/session-tools.ts.
  • Session MCP selection, headers, and internal server config live in packages/api/src/server/background/session/mcp-config.ts.
  • Internal MCP server entrypoints live under packages/api/src/server/mcp/.
  • Isolate/local session tools live under packages/api/src/server/background/isolate/.
  • Effect API schemas and routes live under packages/api/src/http/ and packages/api/src/server/effect/.

When adding or changing a tool:

  1. Put user/session-visible identifiers in the shared package first.
  2. Normalize and validate user-selected tools at the boundary where tools enter session state.
  3. Register MCP tools with stable, action-oriented names and descriptions that state what the tool returns.
  4. Keep authorization and selection outside the runtime. The MCP server should only register tools attached to the current session.
  5. Dispatch from the tool registration into a shared runtime function. Do not fork source-specific logic into separate MCP servers unless the protocol or auth model is actually different.
  6. Preserve isolate behavior. Docs-only sessions must not require an attached repository.
  7. Update tests at the contract, MCP config, runtime, and Worker route levels when the public tool surface changes.

Internal MCP Rules

  • Use one MCP server when tools share auth, transport, and runtime dependencies.
  • Expose each selected capability as its own MCP tool in tools/list.
  • Keep custom MCP servers separate from predefined internal tools. Reject custom names that collide with reserved internal server names.
  • Keep follow-up streamable HTTP requests working by preserving header-based source selection and the D1 session fallback via x-c0-session-id.
  • Keep tool input schemas narrow. Prefer query: z.string().min(1) for search tools unless the caller genuinely needs more control.
Show full SKILL.md (230 more words)Show less

AI Search Source Pattern

AI Search resources in this repo use a common shape:

text
docs in R2 -> Cloudflare AI Search vector index -> shared MCP runtime -> source-specific MCP tools

For a new AI Search-backed document source:

  1. Create or adopt the R2 + AI Search resource with createAiSearchR2 in apps/api/infra/resources.ts.
  2. Add the source id to the aiSearchSourceIds map returned by createAgentResources.
  3. Bind the map through AI_SEARCH_SOURCE_IDS_JSON in apps/api/infra/index.ts.
  4. Add public source metadata in packages/shared/src/session-tools.ts.
  5. Add runtime config in packages/api/src/server/mcp/ai-search-sources.ts, keeping maxResults explicit and source IDs resolved through the shared map.
  6. Register the source in packages/api/src/server/mcp/ai-search-server.ts.
  7. Run the MCP integration tests and update any session UI source picker affected by the new source.

Each AI Search source should expose two MCP tools:

  • search_*: calls the shared runtime with mode: "search" and returns retrieval-only source results.
  • ask_*: calls the shared runtime with mode: "aiSearch" and returns a generated answer plus retrieved sources.

The runtime belongs in packages/api/src/server/mcp/ai-search-runtime.ts. It should accept the source id, query, runtime context, and required mode, then call the configured AI Search binding. Do not add default-mode or old-env fallbacks; source differences should come from registry metadata and runtime config.

Runtime-Configured AI Search Sources

AI Search sources are created and maintained through the runtime registry. Do not hardcode source ids, labels, domains, or document collections in this skill; each deployment chooses its own sources.

Validation

Run focused checks while iterating:

bash
nub exec vitest run tests/integration/ai-search-mcp.test.ts tests/integration/session-mcp-config.test.ts

Before handoff, run the repo-root checks required by AGENTS.md:

bash
nub run typecheck
nub run lint
nub run format

© Consensys, LGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/mcp-tools of Consensys/c0.

Open the folder on GitHubat commit e7a1810

Compare with similar skills

MCP Tools next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

MCP Tools compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
MCP Tools this skillConsensys/c0105—~1.1kAutomated safety check: PassLGPL-3.0
Agents SDKcloudflare/skills3k2 repos~3kAutomated safety check: PassApache-2.0
Turnstile Testingjumodada/Drissionpage-MCP-Server487—~1.7kAutomated safety check: PassCustom licence
Memoraagentic-box/memora731—~813Automated safety check: PassMIT
MCP QAgetsentry/toolkit918—~1.3kAutomated safety check: PassCustom licence
Building MCP Server On CloudflareCommandCodeAI/agent-skills132—~1.5kAutomated safety check: PassMIT

Similar skills

  • Agents SDK

    cloudflare/skills

    Official

    Build, debug, or review Cloudflare Agents SDK applications using the agents package.

    3k GitHub starsUsed in 2 repos~3k tokens
    Agent WorkflowsAuto-check passed

  • Turnstile Testing

    jumodada/Drissionpage-MCP-Server

    A skill your agent uses when testing an authorized Cloudflare Turnstile integration or operating an authorized production challenge with drissionpage-mcp.

    487 GitHub stars~1.7k tokensUpdated 25 days ago
    Agent WorkflowsAuto-check passed

  • Memora

    agentic-box/memora

    A skill your agent uses when working with persistent memory across sessions, storing/retrieving knowledge, managing TODOs/issues, or when context from previous sessions would be helpful.

    731 GitHub stars~813 tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed

  • MCP QA

    getsentry/toolkit

    Official

    QA MCP tool changes with local CLI and real agent clients. An agent skill from getsentry/toolkit.

    918 GitHub stars~1.3k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Building MCP Server On Cloudflare

    CommandCodeAI/agent-skills

    Builds remote MCP (Model Context Protocol) servers on Cloudflare Workers with tools, OAuth authentication, and production deployment.

    132 GitHub stars~1.5k tokensUpdated 7 mo ago
    Agent WorkflowsAuto-check passed

  • MCP Dynamic Orchestrator

    secondsky/claude-skills

    Dynamic MCP server discovery and code-mode execution via central registry.

    227 GitHub stars~1.5k tokensUpdated 11 days ago
    Agent WorkflowsAuto-check passed

More from Consensys/c0

All 11 skills in this repo

  • Debug Cloudflare Workers Observability

    Consensys/c0

    Debug deployed Cloudflare Workers using the cfobservability MCP, Wrangler, D1/R2 state, repo evidence, and safe live reproduction.

    105 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check: notes

  • Deslop Typescript

    Consensys/c0

    Run a final de-slopping pass on nearly finished JavaScript or TypeScript work before commit or PR.

    105 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed

  • Implement Workflow Node

    Consensys/c0

    A skill your agent uses when adding, changing, or reviewing Workflow Nodes in the c0 agent repo, including shared node catalog metadata, Workflow Node options and ports, runtime node Adapters…

    105 GitHub stars~943 tokensUpdated 1 mo ago
    Auto-check passed

  • Workflow Runtime Abi

    Consensys/c0

    Guidance for safely changing the c0 Workflow runtime ABI, manifest ABI, runtime kernels, manifest migrations, workflow artifact compatibility, and audit/backfill tooling.

    105 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

  • Agent Eval Loop

    Consensys/c0

    Run and improve the c0 agent evaluation loop using the local and remote Cloudflare MCP harness, versioned history notes, and current Cloudflare product updates.

    105 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Alchemy Env Types

    Consensys/c0

    Derive Cloudflare worker env types from Alchemy resource Env types instead of hand-writing env shapes.

    105 GitHub stars~707 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about MCP Tools

What does MCP Tools do?

A skill your agent uses when adding, changing, or reviewing MCP servers, MCP tools, session tools, tool registration, Cloudflare AI Search sources, AI Search ingestion resources, or the AI Search…. MCP Tools is an agent skill from Consensys/c0. Use when adding, changing, or reviewing MCP servers, MCP tools, session tools, tool registration, Cloudflare AI Search sources, AI Search ingestion resources, or the AI Search MCP server in this repo.

When should I use MCP Tools?

MCP Tools fits situations like: reviewing MCP servers; tool registration; cloudflare AI Search sources; AI Search ingestion resources.

How do I install MCP Tools in Claude Code?

Run `npx skills add Consensys/c0 --skill mcp-tools -a claude-code`. Or copy the skill folder (.agents/skills/mcp-tools in Consensys/c0) into .claude/skills/mcp-tools in your project. Claude Code loads it when a task matches its description.

How do I install MCP Tools in Codex?

Run `npx skills add Consensys/c0 --skill mcp-tools -a codex`. Or copy the skill folder (.agents/skills/mcp-tools in Consensys/c0) into .agents/skills/mcp-tools in your project. Codex loads it when a task matches its description.

Can I use MCP Tools in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Consensys/c0 --skill mcp-tools -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcp-tools, .gemini/skills/mcp-tools, .github/skills/mcp-tools and .opencode/skills/mcp-tools in your project.

What does MCP Tools need to run?

SKILL.md names no scripts, command-line tools or credentials: MCP Tools is instructions for the agent only.

Does MCP Tools access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is MCP Tools safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does MCP Tools use?

MCP Tools is published under the LGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does MCP Tools use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to MCP Tools?

Skills that share tags, products or a category with MCP Tools: Agents SDK (cloudflare/skills, 3k stars), Turnstile Testing (jumodada/Drissionpage-MCP-Server, 487 stars), Memora (agentic-box/memora, 731 stars) and MCP QA (getsentry/toolkit, 918 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains MCP Tools?

Consensys (a GitHub organization) maintains it in Consensys/c0, which has 105 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on August 18, 2026.

Source: Consensys/c0 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.