account_list
ChatGPTList 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.
account_switch
ChatGPTSet the active billing context. Accepts a slug (e.g. "personal", "team:nd7fx…") or team ID.
agent-readiness__check_readiness
ChatGPTCheck how ready a website is for AI agents: runs about 14 checks in parallel (robots and sitemap, markdown version, MCP and agent manifests, OpenAPI, OAuth/OIDC, agent payment protocols) and returns one score with what to fix first.
brain_add
ChatGPTCreate 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.
brain_admin
ChatGPTBrain 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", or "run_now". Team admin role required for team_sleep actions.
brain_delete
ChatGPTArchive a brain page. It will no longer appear in searches or tool consultations.
brain_expand
ChatGPTRetrieve 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 (not all pages do — drawers are a Step 4 feature for allowlisted tools only).
brain_lint
ChatGPTRun maintenance checks on your brain: find stale pages, orphaned knowledge, and other issues.
brain_query
ChatGPTSearch 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").
brain_settings
ChatGPTView and toggle your brain settings. Currently supports: drawers_enabled (store raw tool output alongside summaries for richer recall).
brain_status
ChatGPTView brain page counts and recent pages for your personal and team brain.
brain_update
ChatGPTEdit 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. Moving a page to team scope requires team admin role.
brain_wings
ChatGPTList the top-level areas ("wings") of your knowledge brain, such as "engineering" or "family". For each area returns its sections, page count and last-updated time, which can narrow a brain search.
case-law__citation_analysis
ChatGPTMap a court case's citation network: what it cites and what cites it, so you can judge its influence and find related authority.
competitor-research__research_competitor
ChatGPTTurn a competitor's URL into one intelligence report: company overview, brand, technology, SEO position, hiring, public discussion and history, assembled from many research steps into a single structured result.
connector_list
ChatGPTList 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 MCPs you can connect.
connector_permissions
ChatGPTView 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" with tool_name + rules to update one. Team scope requires admin role.
connector_remove
ChatGPTDisconnect a connector. Pass slug.
construction-manager__check_property_constraints
ChatGPTCheck a property's planning and development constraints in one pass (for example conservation areas, listed buildings, flood zones and protected land), combining many official datasets into one summary.
contract-opportunities__match_supplier_profile
ChatGPTFind public-sector contracts a company could bid on: searches official procurement portals and ranks live opportunities against the supplier's profile (classification codes, geography, contract value and deadlines).
credits_balance
ChatGPTCurrent balance, plan tier, rate limits, and any negative-balance warnings for the active context.
credits_usage
ChatGPTUsage summary or history. Pass scope: "me" | "team" and detail: "tool" | "skill". Sorted by cost with _others rollup.
deep-research__research
ChatGPTResearch any topic in depth: explores multiple web sources, cross-references claims and returns a structured report with citations.
discover
ChatGPTFind 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 and examples. Flow: prefer route({ intent }) to pick and run a tool. Use discover when you need schemas or a listing, then call use_tool(tool, skill, input). Every discover response also includes a top-level connectors array listing SaaS accounts the user has already connected (LinkedIn, Google, Notion, etc.). Use that to pick the right tool and account without asking — e.g. if connectors shows LinkedIn, the linkedin-post tool is ready to use. Categories: data, media, search, marketing, development, communication, analytics, productivity, ai, finance, security, infrastructure
feedback_debug
ChatGPTReport 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 relevant ToolRouter errors, call IDs, non-sensitive input shape, retries, and expected behavior. Do not include chat history, unrelated conversation text, uploaded file contents, personal data, API keys, or secrets. Reports are stored and reviewed within hours. Skip this for expected errors like invalid input, missing credentials, insufficient balance, rate limits, or genuine "not found" results — those aren't bugs. Limit: 5 reports per hour.
feedback_request_tool
ChatGPTAsk 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 straight to the team. Limit: 5 per hour.
feedback_review
ChatGPTSubmit a review or star rating.
file_delete
ChatGPTDelete a file. Cannot be undone. For team files: requires owner/admin role.
file_list
ChatGPTList or search files. Optional query triggers semantic search. Supports section, tags, plan_status, limit, cursor filters.
file_read
ChatGPTRead a file's full content. Text files return content inline. Binary files (images, video) return a download URL.
file_write
ChatGPTCreate 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".
grants-finder__match_applicant_profile
ChatGPTFind grants an organisation or researcher could apply for: searches official grant portals and ranks live opportunities against the applicant's profile (geography, applicant type, sector and deadlines).
invoice_list
ChatGPTList invoices for the active billing context.
job_cancel
ChatGPTCancel a running job.
job_get
ChatGPTGet job status and result. Returns status: running | completed | failed and result when terminal. Keep polling until you get a terminal status.
job_list
ChatGPTList your active and recent jobs. Optional status filter.
outfit_list
ChatGPTList your outfits.
persona_list
ChatGPTList your personas.
product_list
ChatGPTList your products.
record-collector__collection_value
ChatGPTValue a record collection: matches each item to its exact release and prices it from marketplace data, returning a valued inventory.
route
ChatGPTSend a natural-language intent and optionally any dimensions you already know (tool, skill, model, input fields). Fills only the blanks via Jev, then either executes the call or returns a ready-to-run use_tool payload. Explicit values are never overridden. Returns candidates when confidence is low or no tool fits. Flow: route → if confident and complete, result is returned; otherwise use the pre-filled call with use_tool.
scene_list
ChatGPTList your scenes.
seo__analyze_page
ChatGPTFull on-page SEO check of one URL: title, meta, headings, images, links, content length and structured data, returned as a scored report with specific fixes.
seo__crawl_site
ChatGPTAudit a whole website for search: crawls up to 100 pages from the sitemap and returns one scored report with separate technical, content and answer-engine findings and a prioritised fix list. Runs on ToolRouter's own analysis engine.
stock-market__analyst_insights
ChatGPTAnalyst-grade view of one stock: multi-timeframe technical signals, valuation and analyst consensus combined into one summary.
supply-chain-risk__batch_risk
ChatGPTScore up to 10 exact package versions for security risk in one request. Combines OSV, GitHub advisories, CISA known-exploited vulnerabilities, EPSS exploit likelihood, OpenSSF Scorecard and deps.dev into one ranked risk table.
use_tool
ChatGPTRun a Toolrouter catalogue tool. Prefer route with a natural-language intent when the tool is unknown; otherwise pass exact tool and skill names from discover. The selected tool may read, create, update, publish, send, overwrite, or delete data in Toolrouter or an authorized external service. Rely on ChatGPT confirmation before consequential actions. Long-running calls return a job_id that can be checked with job_get.