Skip to main content
Glama
fosferon

gc_mcp

by fosferon

gc_dispatch

Dispatch agents on demand with task assignments, inspect available targets, providers, and models, preview dispatch resolution, and track job status and output through a unified management interface.

Instructions

On-demand agent dispatch. Spawn an agent with a task, inspect dispatchable targets, inspect provider/model availability, preview dispatch resolution, check job status, retrieve output. Actions: dispatch (spawn agent), list_agents (local markdown agents only), list_providers (show valid provider overrides and availability), list_models (show provider model inventories with authoritative vs hint provenance), resolve_dispatch (preview what provider/model/mode GC would use for one target), list_targets (all dispatchable targets, optionally filtered by kind), status (check job), output (get result), list (query jobs), dismiss (hide noisy job), delete (remove one), prune (bulk cleanup), repair_stale (reconcile ghost running jobs after crashes/redeploys). Default is fire-and-forget (returns job_id immediately). Set wait=true to block until done.

Use gc_dispatch for assignments and runnable work. If you want an ongoing dialogue with an external A2A peer (for example Pluto), use gc_peer_conversation instead — that path preserves session/thread semantics and avoids creating one job per turn. Do not inspect past sessions to guess provider/model defaults. Use list_agents, list_providers, list_models, and especially resolve_dispatch instead.

Semantics:

  • provider = GC dispatch route, not upstream vendor and not CLI binary name

  • model = real provider-native model id only

  • resolve_dispatch shows provider_type, binary, model_source, and model_resolution so you can see exactly what GC will do

Provider selection (dispatch backend / route):

  • Default: omit provider and let the daemon resolve from the agent's declared provider/model fields plus configured fallback order

  • provider: "native" — explicit in-process/native dispatch route

  • provider: "native:" — explicit native backend pin, for example provider: "native:zai"

  • provider: "claude" | "droid" | "pi" — explicit built-in CLI route override

  • provider: "kimi" — explicit dynamic CLI route override when kimi is installed

  • provider: "" — any other installed CLI route label or alias accepted by the daemon

  • action=list_providers — inspect the currently valid native + CLI route strings before choosing one

Model selection:

  • For CLI providers with model_resolution=provider_runtime, omit model unless you know a valid provider-native model id

  • Never pass transport labels such as "kimi-cli" or "claude-code-cli" as model values

  • action=list_models shows exact live inventories where GC can verify them, and clearly labeled hints otherwise

Claude-specific permission controls:

  • permission_mode: default|auto|dontAsk|acceptEdits|plan|bypassPermissions

  • dangerously_skip_permissions: true adds --dangerously-skip-permissions

  • allow_dangerously_skip_permissions: true adds --allow-dangerously-skip-permissions

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNoWorking directory (optional, defaults to project default)
kindNoTarget filter for list_targets (default: all)
taskNoTask text (required for dispatch)
waitNoIf true, block until agent completes (default: false)
agentNoAgent name to dispatch (required for dispatch)
forceNoForce deletion of running job (for delete)
issueNoBee issue ID to link (optional)
limitNoMax rows to return/delete (list/prune)
modelNoExplicit real model id override, or a model hint for list_providers/resolve_dispatch (e.g. "claude-sonnet-4-6", "claude-opus-4-6", "gpt-5.2-codex"). Do not pass CLI labels such as "kimi-cli" or "claude-code-cli". Default: agent-defined, GC default, or provider runtime default depending on resolve_dispatch.
actionYesAction to perform
job_idNoJob ID (for status/output actions)
reasonNoDismiss reason (for dismiss)
statusNoFilter by status (for list/prune)
add_dirNoClaude only: additional directory to allow tool access to
dry_runNoPreview repair_stale without mutating
timeoutNoMax lifetime of the dispatched CLI subprocess. Integer seconds (default: 1800 / 30 min), or "infinite"/"infinity"/"none" to disable the wrapper kill entirely. Accepts string-of-int ("600") so LLM stringification is safe.
providerNoExplicit GC dispatch route override, or route hint/filter for list_providers, list_models, or resolve_dispatch. This is not the upstream vendor and not the CLI binary name. Accepts dynamic CLI route labels such as "claude", "droid", "pi", "kimi", plus "native" or "native:<backend>" such as "native:zai".
scheduledNoFilter scheduled jobs only (for list)
on_completeNoTerminal hook for dispatch. Currently supports "notify" to emit a mailbox event when the job finishes.
since_hoursNoOnly jobs newer than N hours (for list)
allowed_toolsNoClaude only: comma-separated allowed tools
include_hiddenNoInclude hidden jobs (list/prune; default false)
permission_modeNoClaude permission mode override (passed as --permission-mode)
disallowed_toolsNoClaude only: comma-separated disallowed tools
older_than_hoursNoMinimum age in hours for prune (default 24)
older_than_minutesNoMinimum age in minutes for repair_stale (default 30)
dangerously_skip_permissionsNoClaude only: pass --dangerously-skip-permissions
allow_dangerously_skip_permissionsNoClaude only: pass --allow-dangerously-skip-permissions
Behavior4/5

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

With no annotations provided, the description carries the full burden. It thoroughly discloses the default fire-and-forget behavior vs wait=true blocking, explains provider route semantics (provider = GC dispatch route, not upstream vendor/CLI binary), clarifies model selection rules, and documents Claude-specific permission flags. There are no annotations to contradict. The one gap: the description doesn't disclose side effects of delete/prune/dismiss operations or auth requirements, but the semantics sections are quite rich.

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 information-dense and well-organized with clear sections (Actions, Use cases, Semantics, Provider selection, Model selection, Claude-specific permission controls). It's front-loaded with the core purpose and action list. Some redundancy exists (provider semantics repeated between 'Semantics' and 'Provider selection' sections), but this is minor given the tool's complexity. Given 28 parameters and 13 actions, this length is justified.

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?

This is a highly complex tool (28 params, 13 actions, multiple provider routing schemes) with no annotations and no output schema. The description is remarkably complete: it covers all action types, provider selection nuances, model selection constraints, the fire-and-forget vs wait behavior, Claude permission controls, and the relationship to sibling gc_peer_conversation. Given the complexity, the description is thorough enough for an agent to use nearly every action correctly without external documentation.

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 baseline is 3. The description adds significant value beyond the schema: it explains the distinction between provider routes ('native', 'native:<backend>', 'claude', 'droid', 'pi', 'kimi'), clarifies that model should be a real provider-native id not a transport label, and documents permission_mode values with their CLI flag mappings. This meaningfully enriches the 28 parameters, though the description doesn't touch every parameter individually (e.g., issue, limit, since_hours defaults).

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?

The description explicitly names the tool as 'on-demand agent dispatch' with a clear list of 13 actions (dispatch, list_agents, list_providers, list_models, resolve_dispatch, etc.), each with a parenthetical explanation. It clearly states the default fire-and-forget behavior and distinguishes from the sibling gc_peer_conversation which handles ongoing dialogue. This is a specific verb+resource definition with strong sibling differentiation.

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?

The description provides explicit when-to-use guidance: 'Use gc_dispatch for assignments and runnable work' and directly names the alternative: 'If you want an ongoing dialogue with an external A2A peer... use gc_peer_conversation instead.' It also gives action-oriented instructions like 'Do not inspect past sessions to guess provider/model defaults. Use list_agents, list_providers, list_models, and especially resolve_dispatch instead.' This is exemplary usage guidance.

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

Install Server

Other Tools

Latest Blog Posts

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/fosferon/gc_mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server