← Registry

General Tools

ableandagent.com

Provides general-purpose tools through the Model Context Protocol.

2 endpoints17 known toolsFirst detected October 11, 2026Last detected October 11, 2026

ENDPOINT 1

https://mcp.ableandagent.com

No auth detected

MCP server metadata

Name
able-and-agent
Version
1.0.0
Capabilities
tools.listChanged
Server instructions

Able and Agent (https://ableandagent.com) is a marketplace where an AI Agent, acting for a person or organization — its Principal — commissions a Human to do a task in the physical world, such as a pickup and drop-off or photographing a place, and pays when the work is done. Each task is an ACT, an Agent Commissioned Task. It is launching in San Diego, California, by invitation. To ask for access, from San Diego or anywhere else, call register_interest with your Principal's name and email address, your operator's email address, and the city your errands would be in. A link to confirm the request goes to the Principal; we read it once it is followed, and when there is room in that city we email the Principal an invite code. Feature requests are welcome in the same call. An Agent that already has a key from its Principal sends it in the Authorization header, "Bearer aak_…", and may use the ACT tools: accept_terms, get_catalog, commission_act, get_act, list_events, list_messages and send_message. The first call after a quiet spell can take up to 15 seconds while the service wakes. Wait for it rather than retrying; the tools that write take an idempotencyKey, so a retry never does a thing twice.

Known tools 8

register_interest

Ask for access for your Principal, from San Diego or any other city: Able and Agent is launching by invitation, and these requests are how we choose who comes in and where we open next.

Inferred read-only
accept_terms

Accept the Master Terms in force for your Principal, as POST /api/v1/terms/accept: needed before the first ACT.

Potential side effects
get_catalog

Every category, and every market with its communities, neighborhoods and ZIP codes, as GET /api/v1/catalog.

Inferred read-only
commission_act

Create an ACT and fund it, as POST /api/v1/acts: the same fields, in integer US cents and RFC 3339 instants with an offset.

Potential side effects
get_act

One of your ACTs as it stands, as GET /api/v1/acts/{id}.

Inferred read-only
list_events

Everything that happened on your ACTs, in order, as GET /api/v1/events: give after to read on from the last one you saw.

Inferred read-only
list_messages

Every chat message from Humans about your ACTs, as GET /api/v1/messages.

Potential side effects
send_message

Answer a Human in one conversation, as POST /api/v1/conversations/{id}/messages.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.able-and-agent]
url = "https://mcp.ableandagent.com"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "able-and-agent": {
      "type": "http",
      "url": "https://mcp.ableandagent.com"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: able-and-agent
Remote MCP URL: https://mcp.ableandagent.com

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "able-and-agent": {
      "url": "https://mcp.ableandagent.com"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "able-and-agent": {
      "type": "http",
      "url": "https://mcp.ableandagent.com"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "able-and-agent",
  "transport": "streamable-http",
  "url": "https://mcp.ableandagent.com"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 2

https://mcp.sandbox.ableandagent.com

No auth detected

MCP server metadata

Name
able-and-agent-sandbox
Version
1.0.0
Capabilities
tools.listChanged
Server instructions

Able and Agent (https://ableandagent.com) is a marketplace where an AI Agent, acting for a person or organization — its Principal — commissions a Human to do a task in the physical world, such as a pickup and drop-off or photographing a place, and pays when the work is done. Each task is an ACT, an Agent Commissioned Task. This is the sandbox: everything works as on the live site, but no money moves and no Human is sent anywhere. A person at Able and Agent plays the Human, so expect a claim in hours, not seconds. Start with register_agent, giving your Principal's name and email address. It returns a key: send it in the Authorization header, "Bearer aak_…", or as the key argument of every other tool. Then accept_terms, get_catalog for the codes an ACT names, and commission_act. Your Principal is emailed a link to claim the sandbox; an Agent nobody claims stops working after 60 days. An Agent may hold 25 open ACTs at once. The first call after a quiet spell can take up to 15 seconds while the service wakes. Wait for it rather than retrying; the tools that write take an idempotencyKey, so a retry never does a thing twice.

Known tools 9

register_agent

Register yourself in the sandbox and get a key — the first call.

Inferred read-only
resend_claim_link

Email your Principal another link to claim the sandbox, or to confirm you, when the first was lost.

Potential side effects
accept_terms

Accept the Master Terms in force for your Principal, as POST /api/v1/terms/accept: needed before the first ACT.

Potential side effects
get_catalog

Every category, and every market with its communities, neighborhoods and ZIP codes, as GET /api/v1/catalog.

Inferred read-only
commission_act

Create an ACT and fund it, as POST /api/v1/acts: the same fields, in integer US cents and RFC 3339 instants with an offset.

Potential side effects
get_act

One of your ACTs as it stands, as GET /api/v1/acts/{id}.

Inferred read-only
list_events

Everything that happened on your ACTs, in order, as GET /api/v1/events: give after to read on from the last one you saw.

Inferred read-only
list_messages

Every chat message from Humans about your ACTs, as GET /api/v1/messages.

Potential side effects
send_message

Answer a Human in one conversation, as POST /api/v1/conversations/{id}/messages.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.able-and-agent-sandbox]
url = "https://mcp.sandbox.ableandagent.com"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "able-and-agent-sandbox": {
      "type": "http",
      "url": "https://mcp.sandbox.ableandagent.com"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: able-and-agent-sandbox
Remote MCP URL: https://mcp.sandbox.ableandagent.com

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "able-and-agent-sandbox": {
      "url": "https://mcp.sandbox.ableandagent.com"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "able-and-agent-sandbox": {
      "type": "http",
      "url": "https://mcp.sandbox.ableandagent.com"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "able-and-agent-sandbox",
  "transport": "streamable-http",
  "url": "https://mcp.sandbox.ableandagent.com"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.