Skip to content
Agentmart
Submit a tool

reevesagents

Spawn, read and steer AI coding CLIs (Claude Code, Codex, Kimi and more) in local tmux windows.

Connector by mertkayacs · GitHub account verified by the MCP Registry

IndexedApache-2.0Local (stdio)★ 107
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/mertkayacs-reevesagents

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Spawn, read and steer AI coding CLIs (Claude Code, Codex, Kimi and more) in local tmux windows.

Use cases: agent-orchestration

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Runs code on install

Its package runs an install script (such as npm postinstall or setup.py code) as soon as you install it, before any tool is called. Read the script first.

Tools
12 read · 12 write · 5 delete · 2 not yet classified
Secrets
None asked for
Install scripts
Runs code on install
Runs as
Node.js package

Tools by what they do 31

Read from the source code; the running server may list different tools.

Read 12 · Look things up without changing anything.

  • check_approval
  • doctor
  • get_config
  • list
  • list_approvals
  • list_history
  • list_hosts
  • list_presets
  • list_providers
  • list_tools
  • read
  • request_approval

Write 12 · Create, change, send or run things.

  • attach_host
  • detach_host
  • install_skills
  • interrupt
  • resolve_approval
  • save_preset
  • send_key
  • send_text
  • set_config
  • spawn
  • start_preset
  • stop

Delete 5 · Delete, drop, revoke or wipe things.

  • delete
  • delete_history
  • delete_preset
  • delete_run
  • kill

Not yet classified 2 · We could not tell from the name and description.

  • open
  • reap

Files it touches

  • Any path the agent passes to its tools

Tools (31)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • attach_host

    Attach the reevesagents-win MCP to one host CLI by its key (from list_hosts), or to every installed host when key is omitted. After attaching, that CLI can drive agents through these same tools.

  • check_approval

    Read one approval's current status (pending, approved, denied, or expired) by its approval_id.

  • delete

    Permanently remove one ended agent's record. Kill the agent first; a still-running agent is rejected.

  • delete_history

    Permanently remove one archived run history record by its id (from list_history).

  • delete_preset

    Permanently delete a saved preset by its name (from list_presets). Does not affect any running run.

  • delete_run

    Permanently remove one ended run, archiving it to history. Stop the run first; a still-running run is rejected.

  • detach_host

    Detach the reevesagents-win MCP from one host CLI by its key (from list_hosts).

  • doctor

    Check this machine for running agents: Node version, the ConPTY (node-pty) binding, which provider CLIs are installed, and the registry directory. Returns each check with an ok/warn/fail status. Run it when a spawn fails to see what is missing.

  • get_config

    Read the global reevesagents settings: peek_interval_ms, peek_lines, max_depth, max_agents (the per-run agent cap), ready_delay_ms, max_lifetime_ms (auto-reap agents older than this; 0 disables), default_permissions, and language. Check max_agents here when a spawn is rejected for hitting the cap.

  • install_skills

    Install the reevesagents Agent Skill so skill-aware CLIs (Claude Code, Codex, Kimi, OpenCode) learn to drive reevesagents on their own. Writes one SKILL.md to the two shared skill directories under the home dir. Pass no arguments; call with status omitted to install, or read the returned rows to see where it landed. The user must restart their CLIs to pick it up.

  • interrupt

    Press ctrl-c in one agent to interrupt whatever it is doing.

  • kill

    Stop one agent and tear down its ConPTY. Pass an agent_id from spawn or list.

  • list

    List every live run and the agents in each, with their ids, status, provider, and a live flag (true when this session can still drive the agent). Start here to find a run_id or agent_id for the other tools.

  • list_approvals

    List approval requests, optionally filtered by run_id or status (pending, approved, denied, expired). Use it to find an approval_id to resolve.

  • list_history

    List archived run history: runs that have ended or gone stale. Live runs are in list, not here.

Show 16 more tools
  • list_hosts

    List the AI CLIs on this machine that can host the reevesagents-win MCP and whether it is attached to each. Use it before attach_host or detach_host.

  • list_presets

    List saved run presets: reusable agent-team templates, each with a root agent and workers. Launch a whole team at once by passing a preset name to start_preset.

  • list_providers

    List the CLI providers this machine can launch: id, display name, whether it is installed, aliases, and known models. Pass an id as the provider for spawn.

  • list_tools

    List the helper tool CLIs on this machine (Perplexity, Google Colab, Hugging Face, Ollama): what each is for, whether it is installed, and its state (signed in, or reachable for Ollama), plus an example command and a docs link. They are not spawn providers; run them from your own shell.

  • open

    Open a run or agent in tmux for the user: switch the attached tmux client to a run (its reeves tab) or to a specific agent window. Works for any run, whether this agent started it or not, so you can surface any run for the user on request. No effect when nobody is attached.

  • read

    Read one agent's recent terminal output, ANSI-stripped and secret-redacted. Use it to see what the agent printed or is waiting on. Defaults to the last 20 lines.

  • reap

    Sweep for zombie agents and orphan tmux sessions: ends any agent whose tmux window has died or that is older than max_lifetime_ms when that is set above 0 (see get_config), and kills reeves-*/reevesweb_* sessions no live record owns. Returns each reaped agent with the reason (window-gone or lifetime-exceeded) and its age, plus the killed orphan session names. This runs on its own in the background; call it to force an immediate sweep, e.g. after a crash or before relying on list.

  • request_approval

    Ask for approval before a risky action. Creates a pending approval that a human or another agent clears with resolve_approval, and returns it with its approval_id.

  • resolve_approval

    Approve or deny one pending approval by its approval_id (from list_approvals). An optional note records why.

  • save_preset

    Save a live run's agent line-up as a reusable preset under a name, so the same team can be relaunched later with start_preset. Pass a run_id from list. Re-saving the same name updates it. Note: a captured agent's auth_mode and effort are not stored (they default).

  • send_key

    Press one key in an agent: enter, escape, tab, space, up, down, left, right, backspace, or ctrl-c. Send enter after send_text to submit the pasted text.

  • send_text

    Paste text into one agent at its prompt. This does NOT submit it: follow with send_key enter to send. Use it to give a running agent a new instruction.

  • set_config

    Change one or more global settings and save them. Pass only the fields to change. Counts must be positive integers (ready_delay_ms and max_lifetime_ms may be 0); default_permissions is ask or skip; language is a supported code such as en or tr. Example: raise the per-run agent cap with { "max_agents": 20 }, or auto-kill agents running longer than an hour with { "max_lifetime_ms": 3600000 }. Returns the saved settings.

  • spawn

    Start a CLI agent in its own ConPTY on this machine and return its agent_id (use it with send_text, send_key, read, kill) and run_id. Omit run_id to add the agent to this MCP session run, created on the first spawn so a chain of spawns stays in one run; pass run_id to add it to an existing run. Agents live only as long as this MCP session. Call list_providers for valid provider keys.

  • start_preset

    Launch a new run from a saved preset (see list_presets), starting its root agent and every worker at once. Optionally override the run name and working_dir. Returns the new run and its agents.

  • stop

    Stop a whole run: end every agent in it and tear down their ConPTYs. Pass a run_id from spawn or list.

Compare and alternatives

    Featured in

    Signals

    Stars
    107
    Forks
    13
    Open issues
    1
    Last commit
    Oct 23, 2026 (6 days ago)
    Last release
    Oct 25, 2026 (4 days ago)

    From GitHub (fetched Oct 24, 2026).

    Details

    Registry name
    io.github.mertkayacs/reevesagents
    Version
    2.1.0
    Auth
    No auth
    Packages
    npm reevesagents
    License
    Apache-2.0
    First seen
    Oct 24, 2026
    Last checked
    Oct 26, 2026
    Cite this page

    reevesagents MCP server. Agent Mart. https://agentmart.dev/connectors/mertkayacs-reevesagents (last updated 2026-10-26)