herderp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@herderprevive a previous Claude Code session"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
herderp
A Claude Code plugin: a stdio MCP server wrapping the herdr CLI with curated one-shot tools, plus session necromancy — find and read a previous Claude Code agent session from a herdr "space."
What it does
Curated herdr tools — MCP calls over the
herdrCLI instead of hand-typing it. One tool per resource, each taking anaction, so ~35 CLI subcommands cost six tools rather than thirty-five:herdr_agent—list/get/read/send/focus/rename/start/wait/explain.herdr_pane—list/get/run/close/rename/focus/split/swap/move.herdr_tabandherdr_workspace—list/get/create/rename/focus/close.herdr_worktree—list/create/open/remove.herdr_session_list— herdr's own named server sessions (not Claude Code sessions).
Every result carries a
hintnaming the natural next call, and a missing field is rejected by name (herdr_agent{action:"get"} requires "target") rather than falling through to herdr's usage text. herdr's own integration plumbing (pane report-agent/report-metadata/release-agent) and the interactiveagent attach --takeoverare deliberately not exposed.Necromancy — point at a space (a herdr workspace id, label, project cwd, session name, or nothing) and:
necromancy_find_spaces— scan~/.claude/projects/*and live workspaces, present revivable candidates.necromancy_search_all— search the content of many sessions at once when you know what happened but not where: one entry per matching session (its space, id, match count, a representative snippet, last activity), newest first. Bounded on both ends — how many sessions come back (truncated) and how many session files were read at all (scanned/scanTruncated).necromancy_resolve— turn a herdr agent handle (upublish:1= workspace labelupublish, tab labeled1) straight into the exact live session it addresses, in one shot. Ambiguity and misses come back as candidates / a typed reason to fall through, not a wrong guess.necromancy_list_sessions— enumerate the sessions that lived in a space (disk is authoritative), ranked by recency, marked live vs dead, with a per-session preview and — for live sessions — their herdr handle. Degrades to a still-usable list (marked) if herdr is unreachable.necromancy_anchors— deterministically regex-extract a session's "always grab" set (ask, final state, commits, PRs, versions, files touched, errors, test results, decisions) so a catch-up is grounded on evidence and misses nothing load-bearing. No model call.necromancy_outline/necromancy_search/necromancy_read— read a past session's turns in place: outline its shape, search it by keyword or regex, and pull specific turns back verbatim, all capped on count and bytes.
necromancyskill — drives the find-a-space → list → outline → search → read flow conversationally./herderp:ghostcommand — a one-shot catch-up: reads the previous session, or point it at an agent/space name and/or a session id to read a specific one. Get a plain summary of what it did and where it stopped, plus resume questions. Reading only — it never revives.
Related MCP server: codex-mcp-server
How reading works
Claude sessions persist on disk at ~/.claude/projects/<cwd-slug>/<uuid>.jsonl independent of herdr pane life (the slug maps every non-alphanumeric character in the cwd to - — /, ., _, @ and the rest — without collapsing runs, so prod-_x becomes prod--x). Necromancy enumerates them from disk and reads their turns in place — no pane, no relaunch. The reader parses the raw jsonl, skips empty/oversized/malformed files by stat alone, and validates every session id against a strict UUID regex before touching the filesystem.
Requirements
bunonPATH(the server runs under bun; dependencies auto-install on first launch — nobun installneeded).A running
herdrserver and the Claude Code session store at~/.claude/projects. Both degrade gracefully with a clear message if absent.
Install
Via the rtd marketplace:
/plugin marketplace add ryanthedev/rtd-claude-inn
/plugin install herderp@rtdDevelopment
bun install
bun test # unit + integration (side-effect-free)
bun run start # boot the MCP server on stdioScope (v1)
Claude agents only; reading only (find, list, and read past sessions in place). Non-Claude agent kinds are a later seam.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseCqualityCmaintenanceWraps the cursor-agent CLI to provide cost-effective tools for repository analysis, code search, planning, and editing. Offloads heavy thinking tasks from the host AI to reduce token usage while maintaining precise, scoped workspace operations.Last updated75MIT
- AlicenseAqualityCmaintenanceBridges Claude and OpenAI's Codex CLI for AI-powered code analysis, generation, and review, with support for session management, web search, and structured output.Last updated6873612ISC
- AlicenseAqualityDmaintenanceWraps Claude Code as tools for MCP clients, enabling autonomous coding tasks via a 4-tool lifecycle with session management, async polling, and permission controls.Last updated415617MIT
- AlicenseAqualityDmaintenanceWraps Anthropic Claude Code CLI as tools, allowing MCP clients to invoke headless Claude Code sessions.Last updated268MIT
Related MCP Connectors
Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.
Live SEO workflow tools for Claude Code, Codex, and AI agents.
User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ryanthedev/herderp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server