Skip to content

opchain

by asfbay-bit · remote · no sign-in to list tools · v2.0.4 · published by GitHub user asfbay-bit

Claude Code / MCP skills for the dev pipeline: discover, spec, design, build, ship, operate.

Changes · 3
CompareRegistry entry

7 tools: 3 change things and 4 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http opchain-skills https://opchain.dev/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

7 tools

Changes things 3Claude Code: ask
  • create_checkpoint_sessionCreate a private server-issued session for checkpoint storage.No findings

    Why it is in this group

    • The name "create_checkpoint_session" says "create": a word for a change.
    Description, as the server wrote it
    Create a private server-issued session for checkpoint storage. Retain the returned sessionId and use it with read_checkpoint/write_checkpoint; never invent or share one.
  • routeMap a request or an /oc-* command to the skill that should handle it, with the entry phase.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Map a request or an /oc-* command to the skill that should handle it, with the entry phase. Use when you're unsure which skill fits.
  • write_checkpointPersist a skill's session checkpoint so progress survives across sessions.No findings

    Why it is in this group

    • The name "write_checkpoint" says "write": a word for a change.
    Description, as the server wrote it
    Persist a skill's session checkpoint so progress survives across sessions. Stores the object as given (any JSON object up to 64 KiB); it does not validate it against the opchain checkpoint protocol, so write the shape the protocol documents.
Only reads 4Claude Code: allow
  • get_orchestratorReturn the shared orchestrator protocol (welcome flow, pipeline map, active-chaining rules).No findings

    Why it is in this group

    • The name "get_orchestrator" says "get": a word for reading.
    Description, as the server wrote it
    Return the shared orchestrator protocol (welcome flow, pipeline map, active-chaining rules). Read once at the start of a session.
  • get_skillReturn the full SKILL.md (the instructions) for one skill id.No findings

    Why it is in this group

    • The name "get_skill" says "get": a word for reading.
    Description, as the server wrote it
    Return the full SKILL.md (the instructions) for one skill id. Load it, then follow it. Read get_orchestrator once before your first get_skill in a session.
  • list_skillsList every opchain skill (id, displayName, description, phases, commands).No findings

    Why it is in this group

    • The name "list_skills" says "list": a word for reading.
    Description, as the server wrote it
    List every opchain skill (id, displayName, description, phases, commands). Call this first to see the concept→ship pipeline.
  • read_checkpointRead a skill's saved session checkpoint (where you left off).No findings

    Why it is in this group

    • The name "read_checkpoint" says "read": a word for reading.
    Description, as the server wrote it
    Read a skill's saved session checkpoint (where you left off). sessionId must be a private token returned by create_checkpoint_session.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Install

Pinned to version 2.0.4. Values in angle brackets are yours to fill in.

claude mcp add --transport http opchain-skills https://opchain.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__opchain-skills__list_skills",
      "mcp__opchain-skills__get_skill",
      "mcp__opchain-skills__get_orchestrator",
      "mcp__opchain-skills__read_checkpoint"
    ],
    "ask": [
      "mcp__opchain-skills__route",
      "mcp__opchain-skills__create_checkpoint_session",
      "mcp__opchain-skills__write_checkpoint"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as opchain-skills. Review it before you use it.