Skip to main content
Glama

Server Details

Human-in-the-loop for AI agents. Submit choices, get a human decision.

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL
Repository
zmarten/meatspace
GitHub Stars
0

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.
Tool DescriptionsA

Average 4.2/5 across 3 of 3 tools scored.

Server CoherenceA
Disambiguation5/5

Each tool has a clearly distinct purpose: ask_human for human interaction, get_service_status for service availability, and provision_api_key for key creation. No overlapping functionality.

Naming Consistency5/5

All tools use a consistent verb_noun pattern in snake_case: ask_human, get_service_status, provision_api_key. The naming is clear and predictable.

Tool Count4/5

With 3 tools, the server is minimal but covers the core workflow of human interaction. However, additional tools for managing API keys or retrieving ask results would be beneficial.

Completeness2/5

The tool set lacks essential features: no way to retrieve a pending ask result, no key management (list/revoke), and no tool to cancel or update an ask. Agents will likely fail to complete workflows involving delayed human responses.

Available Tools

3 tools
ask_humanInspect

Present content to a human and ask them to choose between options. Use this for subjective judgment, approval, preference, or tie-breaks. Avoid using it for deterministic checks or reversible low-stakes choices. The tool waits briefly for a result, then returns pending if the human has not responded yet.

ParametersJSON Schema
NameRequiredDescriptionDefault
titleYesShort title for the request (max 200 chars)
run_idNoOptional workflow run identifier
choicesYes2-4 choices for the human to pick from
contentNoContent for the human to review (text, markdown, HTML, or image URL). Max 50KB.
metadataNoOptional metadata passed through to webhook
trace_idNoOptional trace identifier
agent_nameYesYour agent/tool name (max 100 chars)
confidenceNoAgent confidence between 0 and 1
callback_urlNoOptional HTTPS webhook URL for async notification
content_typeNoHow to render the content. Default: text
decision_reasonNoWhy the agent is escalating this to a human (max 500 chars)
timeout_secondsNoRequest expiry in seconds (default 3600, max 86400)
recommended_optionNoOptional choice id the agent currently recommends
consequence_of_wrong_choiceNoWhy a wrong choice matters (max 500 chars)
get_service_statusInspect

Check whether MeatSpace is available and when to use a human. Call this when deciding whether to escalate a subjective or high-consequence choice.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

provision_api_keyInspect

Create a MeatSpace API key instantly. No authentication required. Returns a Bearer token for use with the ask_human tool. Max 5 active keys per email address.

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYesAgent or tool name (max 100 chars)
emailYesOwner email address

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.