General Tools

agentbag.ai

Provides general-purpose tools through the Model Context Protocol.

2 endpoints9 known toolsFirst detected October 6, 2026Last detected October 6, 2026

ENDPOINT 1

https://agentbag.ai/api/mcp

No auth detected

MCP server metadata

Name: AgentBag site
Version: 1.0.0

Capabilities

tools

Server instructions

AgentBag is an agent management platform. Tools for evaluating it. Every answer comes from the published capability ledger, which states what is not built as well as what is. Start with list_bag_modules. join_waitlist sends data on the user behalf; confirm before calling it.

Known tools 7

list_bag_modules

List every capability module AgentBag ships, each with a published status (live, beta, or bench) and the caveat that goes with it.

Inferred read-only

get_bag_module

Fetch the full published entry for one module: what it does, why it matters, how it works, its status caveat, and its FAQs.

Inferred read-only

search_bag

Answer a natural-language question strictly from the published capability ledger, returning citations to the modules the answer came from.

Inferred read-only

check_workspace_address

Turn a proposed team name into the tenant subdomain it would become, and report whether that label is usable.

Inferred read-only

answer_faq

Answer a common question about AgentBag in machine form: a terse declarative answer plus a flat object of primitive-valued facts you can assert against without parsing prose.

Inferred read-only

get_pricing_status

Report the current pricing position honestly, including the fact that billing is deliberately disarmed and no numbers are published yet.

Inferred read-only

join_waitlist

Submit an email address to the AgentBag waitlist, optionally reserving a workspace address.

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.agentbag-site]
url = "https://agentbag.ai/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentbag-site": {
      "type": "http",
      "url": "https://agentbag.ai/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentbag-site
Remote MCP URL: https://agentbag.ai/api/mcp

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": {
    "agentbag-site": {
      "url": "https://agentbag.ai/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentbag-site": {
      "type": "http",
      "url": "https://agentbag.ai/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentbag-site",
  "transport": "streamable-http",
  "url": "https://agentbag.ai/api/mcp"
}

MCP Inspector

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

ENDPOINT 2

https://agents.agentbag.ai/api/agent-web/directory/mcp

No auth detected

MCP server metadata

Name: indy
Version: 0.1.0

Capabilities

tools

Server instructions

This server is the AgentBag directory of published agents. Search first with find_agent, then put a question to ONE agent with ask_agent, passing the handle the search returned. Every answer is that agent's own — produced from what its owner published, under the owner's rules — and is attributed to the agent, never to AgentBag. A refusal is one sentence and does not say why; do not retry the same question. Only agents whose owners chose to be listed here are searchable, so an agent absent from a search is not evidence that it does not exist.

Known tools 2

find_agent

Search the directory of published agents by topic, name or category.

Inferred read-only

ask_agent

Ask ONE published agent a question and receive ITS answer — generated from the knowledge its owner published, under the owner's own rules.

Inferred read-only

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.indy]
url = "https://agents.agentbag.ai/api/agent-web/directory/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "indy": {
      "type": "http",
      "url": "https://agents.agentbag.ai/api/agent-web/directory/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: indy
Remote MCP URL: https://agents.agentbag.ai/api/agent-web/directory/mcp

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": {
    "indy": {
      "url": "https://agents.agentbag.ai/api/agent-web/directory/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "indy": {
      "type": "http",
      "url": "https://agents.agentbag.ai/api/agent-web/directory/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "indy",
  "transport": "streamable-http",
  "url": "https://agents.agentbag.ai/api/agent-web/directory/mcp"
}

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.