Local MCP

Agent Checkin

agent_checkin

Announces YOU (this agent session) to the mesh: your role, the repo you are working on and what you can do. Call it when you start working and again every few minutes on long tasks — the entry expires after ttl_seconds, so an agent that stops checking in disappears from the directory instead of looking alive forever. You must check in before agent_inbox will deliver anything: you receive what arrives AFTER you show up, not the backlog.

Input Schema

TableJSON Schema

Name	Required	Description
`caps`	No	What this agent can do (e.g. ['merge','deploy'])
`repo`	No	Repo you are working on (e.g. 'local-mcp')
`role`	No	What you are doing (e.g. 'builder', 'reviewer', 'release')
`status`	No	What you are doing RIGHT NOW, one line (e.g. 'porting evernote to Go', 'measuring #1164 on 3674da7e'). agents_list shows it with its age, so peers can tell working from stuck — update it when your task changes.
`agent_id`	Yes	Stable name for this agent session (e.g. 'builder', 'qa', 'release'). Reuse it across check-ins.
`herdr_pane`	No	If you are running inside a Herdr-managed pane (check HERDR_ENV=1 first), your own pane id — e.g. $HERDR_PANE_ID. Registers this agent for #2540's automatic wake: when a Mesh message arrives, a fixed local prompt ('[auto-wake #2540] Hay N mensajes de Agent Mesh; llamá agent_inbox') is submitted to this pane via `herdr agent prompt`, so you get a real turn instead of a silent notification. The '[auto-wake #2540]' prefix is what tells you the turn came from the mesh and not from a person typing the same sentence. Never send the value of a remote message here — only your own pane id. Purely local: never sent to the mesh backend. Omit if you are not in Herdr.
`ttl_seconds`	No	Seconds until this entry goes stale, 60-86400. Omit it and the default comes from `role`: 3600 for an agent that works (builder, reviewer…), 900 for 'ping' and 'verification'. Your presence also renews itself with every mesh call you make, so this is the silence you can afford, not how often you must check in.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedSep 28, 2026
RemovedSep 27, 2026
AddedSep 19, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations mark it as non-read-only and open-world; description elaborates on the side effects: entry expiry, disappearance if not checking in, and the renew-on-call behavior. It reveals the auto-wake integration without contradicting any annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but each sentence carries information; it's front-loaded with the core purpose and then provides necessary details. No filler, though it could be trimmed slightly without losing value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a rich schema, output schema, and detailed description covering when, how, and side effects, an agent has everything needed to call correctly, including prerequisites and nuances like TTL defaults and auto-wake behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description adds default TTL logic based on role, updates status guidance, and explains herdr_pane purpose, adding meaning beyond the schema's short examples.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (announces) and resource (the mesh), and clarifies the session's role, repo, and capabilities. It distinguishes from siblings like agent_inbox and agents_list by focusing on registration/presence.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs when to call (start of work, every few minutes) and explains the expiry mechanism and the dependency on agent_inbox. It also mentions the auto-wake behavior for Herdr panes, giving clear context for when this tool is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Local MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.