Agent Switchboard

HumanLayer

by HumanLayer

Verified

Gates autonomous agent tool calls behind human approval in Slack or email, so high-risk actions require a person to sign off before they execute.

Use it now

Keep it with up to 9 other tools you're setting up, then share them all as one link.

Try this first

Ask your assistant, with HumanLayer connected:

  • Contact Human

    Use HumanLayer to escalate a question from an agent to a person: ‹what you need›

Connect it over MCP

Ask your coding agent to set it up

Connect HumanLayer as an MCP server, following its setup instructions at https://github.com/humanlayer/humanlayer

Its page: github.com/humanlayer/humanlayer

Call the API

Auth An API key from HumanLayer

Its page: github.com/humanlayer/humanlayer

Compare

Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.

Access
APIMCP
Auth
API Key
Skills
3

Skills

  • Require Approval

    Wraps a tool call so it blocks until a designated human approves or rejects the action.

  • Contact Human

    Escalates a question from an agent to a person over Slack, email, or SMS and returns the reply.

  • Approval Audit

    Records who approved which agent action and when, producing an auditable decision trail.

OrchestrationAutonomous AgentsCommunication & Messaginghuman-in-the-loopapproval-workflowagent-safetyslack-approvalsguardrailsfunction-gatingpython-sdk
Visit Agent
humanlayer
Gates autonomous agent tool calls behind human approval in Slack or email, so high-risk actions require a person to sign off before they execute.
try this first
Ask your assistant, with HumanLayer connected:
Use HumanLayer to escalate a question from an agent to a person: ‹what you need›contact-human
use it now
Connect HumanLayer as an MCP server, following its setup instructions at https://github.com/humanlayer/humanlayermcp.setup-prompt
An API key from HumanLayerapi.auth
fields
nameHumanLayer
providerHumanLayer
urlhttps://github.com/humanlayer/humanlayer
categoriesorchestration · autonomous-agents · communication
accessapi · mcp
authapiKey
streamingfalse
pushtrue
verifiedtrue
officialfalse
sponsoredfalse
tagshuman-in-the-loop, approval-workflow, agent-safety, slack-approvals, guardrails, function-gating, python-sdk
skills
require-approvalRequire ApprovalWraps a tool call so it blocks until a designated human…
contact-humanContact HumanEscalates a question from an agent to a person over Sla…
approval-auditApproval AuditRecords who approved which agent action and when, produ…
alternatives
/agents/humanlayer/alternatives8 listedopenbot, pragor, ag2
compare
/compare?a=humanlayer&b=openbot&c=pragorwith openbot, pragor