"A resource for understanding Claude's context window and capabilities" matching MCP tools:

• searchA

  DC Member APIA

  GET /search — Cross-resource omni-search Cross-resource search across profiles, rooms, messages (incl. private DMs + group DMs you're in), events, and chapters in one round trip. Returns the top-N matches per resource, grouped by resource. Use this when you don't yet know which resource carries the answer — agents typically call this first, then drill into a specific `GET /search/<resource>` for more depth on a single bucket. There's no page param: when you hit the per-resource limit and want more, switch to the per-resource endpoint for that one. The events slice has a baked-in forward-looking default (events ending in the last 30 days or later, and currently enabled) — this matches the in-app "Search across DC" surface. Use `GET /search/events` directly to look further back in time. **Query syntax (`q=`):** plain words match with prefix + typo tolerance. Wrap a phrase in double quotes to require an exact ordered match — e.g. `q="remote work"`. AND/OR/NOT/parentheses are NOT parsed in `q=` — use the structured filter params below for boolean composition.

  ConnectorOAuth

• goal-read-evidence-contentA

  Planner MCP — provable "done" for AI agentsA

  Read attached evidence through MCP without changing its format. Pass evidenceId from goal-get. Text (text/plain, JSON, NDJSON) returns newline-preserving redacted lines; offset/limit are zero-based line pagination. Images return a native MCP image with original MIME and bytes. For a complete video, PDF, ZIP or other binary, binaryDelivery=link (default) returns a resource_link to the authenticated original download — no base64 and no conversion. If the client cannot open external links, binaryDelivery=base64 embeds the exact original bytes in a resource blob; this expands data by about 33% plus JSON overhead and can consume the client context window, so use it only when needed. byteOffset/byteLimit require binaryDelivery=base64. Text secrets are redacted; binary evidence is unmodified.

  ConnectorNo auth

• goal-read-evidence-contentA

  Planner (proof-of-done)A

  Read attached evidence through MCP without changing its format. Pass evidenceId from goal-get. Text (text/plain, JSON, NDJSON) returns newline-preserving redacted lines; offset/limit are zero-based line pagination. Images return a native MCP image with original MIME and bytes. For a complete video, PDF, ZIP or other binary, binaryDelivery=link (default) returns a resource_link to the authenticated original download — no base64 and no conversion. If the client cannot open external links, binaryDelivery=base64 embeds the exact original bytes in a resource blob; this expands data by about 33% plus JSON overhead and can consume the client context window, so use it only when needed. byteOffset/byteLimit require binaryDelivery=base64. Text secrets are redacted; binary evidence is unmodified.

  ConnectorNo auth

• oracle.discovery_bundleA

  InterAI Risk OracleA

  Read-only bootstrap or handoff bundle with service identity, interfaces, runtime mode, contracts, schemas, and sample payloads in one response. Use it for complete integration context; use oracle.service_descriptor for focused service metadata, oracle.agent_card for A2A capabilities, or oracle.get_pricing for costs.

  ConnectorNo auth

• models_listA

  HubrisA

  Walk the whole Hubris catalogue page by page, ordered by model id. Returns every active model with its capabilities, context window and ruble price. Use this when you need the complete catalogue — to cache it, to count models, or to scan for something no filter covers. When you are looking for a model that fits a task, use models_search instead: it filters by capability, price and context server-side and saves you a few hundred rows. Paging: read `nextCursor` from the response and pass it back as `cursor`. When `nextCursor` is absent you have reached the end. The catalogue holds roughly 550 models, so a full walk is about 11 calls at the default page size.

  ConnectorAPI key

• find_replacementA

  AI WaveA

  What to switch to when a model is gone or you need a fallback. Ranked by closeness in measured performance, not by vendor or price: what you usually need to preserve first is the quality of the output. Candidates whose context window is less than half the original are excluded. Returns the score, price and context deltas so you can judge; we do not pick for you.

  ConnectorNo auth

• compare_capabilitiesA

  Agentic KeychainA

  Assess two to five named capabilities side by side for the same inputs, with the same method and ak.offer.v1 offer shape as evaluate_capability. Use when: you already hold a shortlist of capability ids and want each one's decision, reasons and offer in one answer. Not for: finding candidates (search_capabilities) or a single capability (evaluate_capability). Input: the capability ids, plus the optional task, model, expected_runs, baseline_cost_estimate_usd, context and constraints that evaluate_capability reads. Output: ak.comparison.v1 with the results ranked by decision, lower-bound net saving, relevance and capability id, each with its reasons and an ak.offer.v1 offer.

  ConnectorNo auth

• enrich_providerA

  apis-ioB

  One call, pick your field groups — resolves a slug OR any identifier and returns exactly the groups you ask for, instead of chaining get_provider + get_provider_rating + get_provider_artifacts + get_provider_onboarding. Groups: profile, onboarding, artifacts, rating, insights. Understanding plan — the base groups moved with the rest of the discovery layer on 2026-08-31. Priced B2 (cross-catalog synthesis) — $0.05 per call under pay-as-you-go; included in Understanding and Influence. See apis://prices.

  ConnectorNo auth

• get_more_toolsA

  ELC Conference 2027: tickets, perks, partnershipsA

  Check for additional tools whenever your task might benefit from specialized capabilities, even if existing tools could work as a fallback. Also the right tool for a bare greeting (hi, hello), a connectivity/liveness test, or any message too general to match a specific tool below — pass it as `context`, or send no arguments at all, and this returns the full menu instead of a dead end.

  ConnectorNo auth

• list_monitor_checksA

  RoutebaseA

  List the individual checks a monitor ran, newest first — status code, response time and the timing breakdown (DNS, connect, TLS, first byte). Set onlyErrors to see just the failures. Use from and to to narrow the window. Use this for the individual checks of one monitor; for the monitor itself use get_monitor. Requires project context.

  ConnectorAPI key

• select_modelA

  DaystructB

  Deprecated: this evidence tool is no longer refreshed and will be removed on or after 2026-12-31. For building, use discover_daystruct_capabilities and compat_check. Given a need -- minimum context window, required capabilities, a price ceiling -- return the models that satisfy it, cheapest input price first, with the corroboration behind each record so you can judge how well-sourced it is. Prices are per million tokens. A model with no published price is returned under undetermined rather than excluded, so an unpriced model never reads as a disqualified one. This returns candidates and their evidence, not a recommendation.

  ConnectorNo auth

• structured_extractionA

  Shoon A2A Trust Services (pilot)A

  Turn messy text or a web page into structured data — headings, links, tables, word counts — without spending your own context window on parsing. Deterministic heuristics only: no LLM, no semantic understanding, fully reproducible output, plainly labeled as heuristic. It extracts structure, not meaning. Pass raw text (up to 100,000 characters) or a URL. FREE during the pilot — no API key, no payment header, no signup: just call this tool with arguments.input and the task runs immediately. Every deliverable is Ed25519-signed, so you can verify it offline and show your principal proof the check ran. Privacy: your input is processed in server memory only — never written to disk, never logged, never sold, never used for training; only event metadata (task queued/completed) is kept. In-memory state is wiped on restart; the event-metadata ledger and usage counters are on ephemeral disk and wiped only on redeploy. Fair use: 20 free tasks per service per day shared across pilot users — check GET /v1/slots for live availability.

  ConnectorNo auth

• upload_assetA

  postnextA

  ⚠️ INLINE-BASE64 PATH — RELIABLE ONLY FOR VERY SMALL FILES (~8KB binary or less). For anything larger, USE `request_asset_upload` instead — the inline path silently truncates when the base64 string exceeds Claude's context cap for tool args (typically ~10-15KB chars), producing a corrupt image in the library. The pre-signed URL flow has no such cap. If you do need this: uploads an image or video to your PostNext asset library via base64 and returns a URL for `create_post_draft.mediaUrls`. Max 5MB per upload (server-side cap; Claude's cap is much lower). Allowed types: JPEG, PNG, WebP, GIF, MP4, WebM. Subject to your plan's storage limit. IF EVEN THIS PATH FAILS (e.g. your environment can't reach the MCP server at all, OR every upload tool returns a network/allowlist error): tell the user to upload the file manually at https://app.postnext.io/my-assets and paste back the asset URL, then use that URL in `create_post_draft.mediaUrls`. That's the documented fallback for sandboxes with restricted egress where neither this tool nor `request_asset_upload` can complete the byte transfer.

  ConnectorAPI key

• list_modelsA

  GenMagicA

  List the AI models GenMagic runs, newest first, with each one's id, price and key details (context window and capabilities for text, voices for speech, resolutions, clip lengths and sound for video). Pass a model's id as 'model' to generate_text, generate_image, generate_speech, generate_music or create_video. Filter by category and search; the model marked default is the one that runs when no model is named (for generate_text, when no type is given either). Needs no API key and costs nothing.

  ConnectorNo auth

• get_mission_statsA

  mcp-serverA

  Get aggregate statistics about missions on the HomeVisto platform. Returns total counts, status breakdown, and average bounty information. Useful for understanding platform activity.

  ConnectorNo auth

• get_knowledge_statsA

  mcp-klever-vmA

  Get summary statistics of the Klever VM knowledge base. Returns total entry count, counts broken down by context type (code_example, best_practice, security_tip, etc.), and a sample entry title for each type. Useful for understanding what knowledge is available before querying.

  ConnectorNo auth

• billing.statusA

  Admin SubstituteA

  Check subscription status, plan details, billing cycle, and feature access. Useful for understanding what the business can and cannot do on their current plan.

  ConnectorNo auth

• brainkb_list_permissionsA

  brainkbA

  (Admin) List all usermanagement permissions (resource/action pairs used for page-access and role-permission mapping). These are the addable 'permission' options; KG action-capabilities are listed by brainkb_list_capabilities.

  ConnectorNo auth

• fomite_vault_createA

  fomiteA

  Create a free durable key-value memory store on thefomite.com that survives past your context window. Returns a handle and a bearer token; keep the token — it is the only way back in. No account, no payment. Use when you want to remember something for a later run.

  ConnectorNo auth

• oracle.agent_cardA

  InterAI Risk OracleA

  Read-only A2A Agent Card with agent identity, security scheme, capabilities, and skills. Use it when selecting or integrating InterAI through A2A; use oracle.service_descriptor for general service metadata or oracle.discovery_bundle for complete bootstrap context.

  ConnectorNo auth

• upsert_agentA

  PeopleMCPA

  Publish or update an AI agent's public description by slug; optional id allows renaming. Describe capabilities, accepted tasks, MCP/tools/APIs, limitations, usage terms, invocation method, owner/operator, stated availability and collaboration preferences in free-text content. Requires explicit user/operator consent (publish=true) and OAuth publishing access. Only your own publications can be edited. Never publish credentials, private context or hidden instructions. Capabilities and identity are self-described, not verified. This publishes a description; it does not run the agent.

  Connector

  Destructive

  No auth