ToolRouter is an MCP server with 47 tools an agent can call, among them account_list, account_preferences, account_setup. It answers at https://api.toolrouter.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 20 October 2026, succeeded.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
account_list | List all billing contexts (personal + teams) or get detail on one. No slug → summary list. With slug → full detail including team members, role, subscription status, and pointers to the team's connectors, credentials, keys, and files. Inputs: slug |
account_preferences | Read or write billing preferences (auto-reload, budget cap, default context). Pass action: "get" to read, action: "set" with fields to write. Inputs: action, default_billing_context, auto_reload_enabled, auto_reload_threshold, auto_reload_amount, budget_limit |
account_setup | Initialize or re-check your account, provision it when needed, and return your user ID and plan. CALL THIS FIRST when the user asks to set up ToolRouter, connect their account, check their account status, or get started. |
account_switch | Set the active billing context. Accepts a slug (e.g. "personal", "team:nd7fx…") or team ID. Inputs: context |
brain_add | Create a new brain page. Knowledge you add here will be available to all future tool calls. Optional wing/room/hall organise the page in the MemPalace hierarchy for sharper retrieval. Inputs: title, content, scope, tags, wing, room |
brain_admin | Brain admin operations. Pass action: "lint" | "link" | "promote" | "rebuild_index" | "team_sleep". team_sleep enables/disables/runs the nightly team consolidation cycle — pass sub_action "enable" (with optional timezone), "disable", "status Inputs: action, page_id, to_page_id, relationship, label, team_id |
brain_delete | Archive a brain page. It will no longer appear in searches or tool consultations. Inputs: page_id |
brain_expand | Retrieve the verbatim source text (a "drawer") linked from a brain page. Use this when a summary lacks specifics you need — drawers contain the original tool output, redacted for credentials. Returns 404 if the page has no linked drawer (no Inputs: page_id |
brain_lint | Run maintenance checks on your brain: find stale pages, orphaned knowledge, and other issues. |
brain_query | Search your knowledge brain for relevant information. Returns pages ranked by relevance. Optional wing/hall narrow the search to a slice of the brain (e.g. wing="engineering", hall="preference"). Inputs: query, scope, limit, wing, hall, include_drawer_previews |
brain_settings | View and toggle your brain settings. Currently supports: drawers_enabled (store raw tool output alongside summaries for richer recall). Inputs: action, setting, value |
brain_status | View brain page counts and recent pages for your personal and team brain. |
brain_update | Edit an existing brain page's content or metadata. wing/room/hall can be patched to re-file a page. scope can be changed to move a page between your personal and team brain — useful when an auto-ingested page landed in the wrong place. Movi Inputs: page_id, content, title, tags, wing, room |
brain_wings | List the wings of your brain — the top-level areas your knowledge is organised under (e.g. "engineering", "family"). For each wing returns the rooms and halls inside, page count, and last-updated time. Use this to discover the right wing/ha Inputs: include_team |
connector_add | Connect a new OAuth account or MCP server. For OAuth: pass type: "oauth", kind: "slack". For MCP catalog: pass catalog_slug. For custom MCP: pass url + auth_type. Inputs: type, kind, catalog_slug, slug, display_name, url |
connector_list | List connected accounts and MCP servers (summary) or detail on one connector. Pass slug for detail including every tool the connector exposes. Optional type: "oauth" | "mcp" filter. Pass include_available: true to also see available catalog Inputs: slug, type, context, include_available |
connector_permissions | View or set permissions for tools on a connected MCP server — which tools are allowed, rate limits, budget caps, argument restrictions. Pass the connector slug (from connector_list) and action: "list" to see current rules, or action: "set" Inputs: slug, action, billing, tool_name, allowed, rate_limit_per_hour |
connector_remove | Disconnect a connector. Pass slug. Inputs: slug, type, billing |
credential_default | Set the default value for a multi-value credential. Inputs: name, label, context |
credential_delete | Remove a saved credential. If label is provided, removes only that specific entry. If no label, removes ALL entries for that credential name. Inputs: name, label, context |
credential_guide | Get setup instructions for a specific credential. Inputs: name |
credential_list | List saved credentials (summary) or detail on one. Pass name for detail view. Pass show_available: true to include the full credential catalog. Inputs: name, context, show_available |
credential_save | Save a credential (BYOK provider API key). Saved keys persist across sessions and are used automatically. Inputs: name, value, label, is_default, context |
credits_balance | Current balance, plan tier, rate limits, and any negative-balance warnings for the active context. |
credits_usage | Usage summary or history. Pass scope: "me" | "team" and detail: "tool" | "skill". Sorted by cost with _others rollup. Inputs: scope, detail, period, limit, offset |
discover | Find the right ToolRouter tool for your task. Describe what you need in plain language. Examples: "analyze a website", "research competitors", "find prospect companies", "check DNS records". Exact tool name (e.g. "seo") returns full schemas Inputs: query, category |
feedback_debug | Report a ToolRouter platform bug that blocks you from completing the user's task. Use this when you suspect the issue is on our side — a tool crashed, returned malformed data, timed out unexpectedly, or behaved inconsistently. Include the r Inputs: tool, skill, error_messages, call_ids, job_id, interaction_log |
feedback_request_tool | Ask ToolRouter to build a tool that does not exist yet. Use this when discover returned nothing useful for what the user needs. Describe the capability in plain terms — do not include personal data, API keys, or secrets. Requests go straigh Inputs: what, why, searched, agent_context |
feedback_review | Submit a review or star rating. Inputs: tool, rating, review |
file_delete | Delete a file. Cannot be undone. For team files: requires owner/admin role. Inputs: file_id |
file_list | List or search files. Optional query triggers semantic search. Supports section, tags, plan_status, limit, cursor filters. Inputs: query, context, section, tags, plan_status, prompt_type |
file_read | Read a file's full content. Text files return content inline. Binary files (images, video) return a download URL. Inputs: file_id |
file_write | Create or update a file. Pass mode: "create" | "update". Binary uploads: call with binary: true to get an upload_url, then PUT bytes, then call with mode: "finalize". Inputs: mode, file_id, name, section, context, content |
invoice_list | List invoices for the active billing context. Inputs: limit |
job_cancel | Cancel a running job. Inputs: job_id |
job_get | Get job status and result. Returns status: running | completed | failed and result when terminal. Keep polling until you get a terminal status. Inputs: job_id |
job_list | List your active and recent jobs. Optional status filter. Inputs: status, limit |
key_create | Create a new API key. Returns the secret once — save it immediately. Inputs: name |
key_delete | Revoke an API key. Refuses to revoke the currently-authenticating key. Inputs: key_id |
key_list | List API keys (summary) or get detail on one key. Pass key_id for detail view. Inputs: key_id |
outfit_list, persona_list, product_list, scene_list, subscription_manage, top_up_credits, use_tool
Every block below points at https://api.toolrouter.com/mcp. Pick your client and copy.
claude mcp add --transport http toolrouter https://api.toolrouter.com/mcp
{
"mcpServers": {
"toolrouter": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.toolrouter.com/mcp"]
}
}
}{
"mcpServers": {
"toolrouter": {
"url": "https://api.toolrouter.com/mcp"
}
}
}{
"servers": {
"toolrouter": {
"type": "http",
"url": "https://api.toolrouter.com/mcp"
}
}
}{
"context_servers": {
"toolrouter": {
"url": "https://api.toolrouter.com/mcp"
}
}
}{
"mcpServers": {
"toolrouter": {
"serverUrl": "https://api.toolrouter.com/mcp"
}
}
}{
"mcpServers": {
"toolrouter": {
"url": "https://api.toolrouter.com/mcp"
}
}
}name: ToolRouter
version: 0.0.1
schema: v1
mcpServers:
- name: ToolRouter
type: streamable-http
url: https://api.toolrouter.com/mcp{
"mcpServers": {
"toolrouter": {
"httpUrl": "https://api.toolrouter.com/mcp"
}
}
}{
"mcpServers": {
"toolrouter": {
"type": "http",
"url": "https://api.toolrouter.com/mcp"
}
}
}{
"mcpServers": {
"toolrouter": {
"url": "https://api.toolrouter.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.toolrouter.com%2Fmcp&type=streamable_http&id=toolrouter&name=ToolRouter
It answered our last check on 20 October 2026 in 201 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
47, as returned by the server's own tools/list on 12 September 2026: account_list, account_preferences, account_setup, account_switch, brain_add, brain_admin, brain_delete, brain_expand, and 39 more.
It answered our last check on 20 October 2026 in 201 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.toolrouter.com/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.humanleap. Endpoint host: api.toolrouter.com. ARD identifier: urn:air:io.github.humanleap:mcp:toolrouter.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.