"A server for finding information about the % token" matching MCP tools:

• get_corpus_coverageA

  SRI — MCP Server InspectorA

  No arguments. Returns how many MCP servers have been read at source level, and the share of them with each category of finding (credential access, network egress, install-time execution, prompt-injection surface). Use this to judge whether checking a specific server is worth it before you look one up. It reports aggregate counts only - no per-server findings, and no verdict about any individual server.

  ConnectorNo auth

• mediora__longitudinal_trendA

  mediora-mcpA

  Return the per-marker trajectory analyser output for the authenticated patient — HbA1c rising, eGFR falling, ferritin depleting, etc. Each finding includes the marker slug, kind, severity (Info / Notice / Important), trend per year, sample count, date range and a supportive headline + detail. Proxies https://api.mediora.ai/api/trajectory/warnings with the user's token forwarded as Authorization: Bearer.

  ConnectorNo auth

• otto_delegation_statusA

  Otto IntelB

  Read back, for the end user identified by a CDP access token, their CDP accounts, whether the Model-B fence is present, and whether an active delegation reads back (with its expiry and the per-swap cap recorded for it). Arguments: { accessToken } — the server resolves the user from the token; a client-sent user id is refused. delegation.per_swap_cap_usd is the number THIS user chose at mint time; it is ABSENT when no cap is recorded for the grant, which means the delegated send will refuse it — say so rather than showing the shared ceiling. fence.per_swap_cap_usd is that shared ceiling and is never a per-user number. Output is bound to that user; nothing about any other user is returned. Server-to-server only: the caller presents Otto's delegation secret in the `x-otto-delegation-auth` request header (never in arguments); a call without it is refused before anything is read. The listed input schema is intentionally permissive — the strict schema is validated after the caller is authenticated.

  ConnectorNo auth

• otto_delegation_revokeA

  Otto IntelB

  Revoke the end user's delegation from Otto's side and confirm by read-back that it no longer exists; from then on this server submits nothing for that user (fail-closed, even if the read-back had failed). Arguments: EITHER { accessToken } (the user path — the server resolves the user from the token) OR { userId, support_reason } (the support path, for an operator holding the server secret; the reason is logged, the token never is). Server-to-server only: the caller presents Otto's delegation secret in the `x-otto-delegation-auth` request header (never in arguments); a call without it is refused before anything is read. The listed input schema is intentionally permissive — the strict schema is validated after the caller is authenticated.

  Connector

  Destructive

  No auth

• admin_search_findingsA

  redm-mcpA

  Admin-only: rank community findings against a natural-language or token `query` using the same hybrid retrieval (vector + PostgreSQL full-text search fused via RRF, reranked) that `semantic_search` uses for the `learnings` category — but with admin fields attached: `id`, `authorIp`, `createdAt`, `linkedNatives`. Use this to find the finding an agent is complaining about, to spot near-duplicates of one before editing/merging, or to audit what a query surfaces. `admin_list_findings` is a plain ILIKE filter; this is relevance-ranked. Optional post-filters: `authorIp` (exact), `tag` (exact). `limit` default 10, max 25. Scoped to THIS deployment's game.

  ConnectorOAuth

• admin_search_findingsA

  RedM McpA

  Admin-only: rank community findings against a natural-language or token `query` using the same hybrid retrieval (vector + PostgreSQL full-text search fused via RRF, reranked) that `semantic_search` uses for the `learnings` category — but with admin fields attached: `id`, `authorIp`, `createdAt`, `linkedNatives`. Use this to find the finding an agent is complaining about, to spot near-duplicates of one before editing/merging, or to audit what a query surfaces. `admin_list_findings` is a plain ILIKE filter; this is relevance-ranked. Optional post-filters: `authorIp` (exact), `tag` (exact). `limit` default 10, max 25. Scoped to THIS deployment's game.

  ConnectorOAuth

• trooth_my_company_recordA

  TroothA

  Needs an OAuth access token for this server from the authorization server its protected-resource metadata names, for a person who has signed in to trooth.co; no scope is required, and every other tool here needs no token. Reads the company record of the Trooth workspace the signed-in person belongs to: its name, its slug and the address of its public page. The workspace comes from the token's subject and never from an argument, so this tool takes no arguments. Read only.

  ConnectorNo auth

• get_hiring_signalA

  CoinBuchaA

  Hiring velocity across tracked Bitcoin and crypto-infrastructure employers, counted from their live ATS boards. Returns { as_of, companies[], note, why, disclaimer }; each company carries company, ticker, category, ats, careers_url, open_roles, open_roles_30d_ago, open_roles_90d_ago and the derived delta_30d, delta_90d and pct_30d. Example: {"company": "coinbase"} for one employer, or {} for every employer tracked. When a company filter matches no tracked employer the response adds coverage_note and tracked_count, saying that the name is outside the tracked set — a limit of coverage, not a finding about whether that company is hiring. Information, not financial advice.

  ConnectorNo auth

• get_hiring_signalA

  bitcoin-signalsA

  Hiring velocity across tracked Bitcoin and crypto-infrastructure employers, counted from their live ATS boards. Returns { as_of, companies[], note, why, disclaimer }; each company carries company, ticker, category, ats, careers_url, open_roles, open_roles_30d_ago, open_roles_90d_ago and the derived delta_30d, delta_90d and pct_30d. Example: {"company": "coinbase"} for one employer, or {} for every employer tracked. When a company filter matches no tracked employer the response adds coverage_note and tracked_count, saying that the name is outside the tracked set — a limit of coverage, not a finding about whether that company is hiring. Information, not financial advice.

  ConnectorNo auth

• models_searchA

  HubrisA

  Find models that fit a task. Filters by name, capability, price ceiling and context window, and can sort the result. This is the tool to reach for when choosing a model — it does the filtering server-side and returns at most 50 rows. All filters combine with AND, and every one of them is optional: calling with no arguments returns the first 50 active models. Two things worth knowing about prices. `maxInputPer1MRub` keeps only models billed per token, because a ruble-per-million ceiling is meaningless for a model billed per image. The `cheap_input` and `cheap_output` sorts push non-token models to the end of the list for the same reason — their token rate reads as zero, which would otherwise put video models at the top of "cheapest".

  ConnectorAPI key

• neuron_logoutA

  neuronB

  Clear the current auth token locally. Does NOT revoke server-side MCP tokens — revoke from the Neuron dashboard (Settings > MCP Tokens) for full invalidation.

  ConnectorNo auth

• list_skillsA

  mcpA

  START HERE for any open-ended request. Lists the task playbooks this server supports — systematic learning from bookmarks, organising into themes, cleaning up, X-list intelligence, exporting data out, finding a half-remembered save, digests, and diagnosing sync. Each names when to use it; call get_skill for the exact tool sequence.

  ConnectorNo auth

• goal-register-iteration-findingA

  Planner (proof-of-done)A

  Register an immutable LeanSolver finding against the currently tracked goal contract. subjectRefs must be goal-scoped refs of kind goal, criterion, or assumption. Returns the server-generated finding id to pass later as addressesFindingId; rejects stale contract tracking.

  ConnectorNo auth

• goal-register-iteration-findingA

  Planner MCP — provable "done" for AI agentsA

  Register an immutable LeanSolver finding against the currently tracked goal contract. subjectRefs must be goal-scoped refs of kind goal, criterion, or assumption. Returns the server-generated finding id to pass later as addressesFindingId; rejects stale contract tracking.

  ConnectorNo auth

• verify_emailA

  AientA

  Confirm the code Aient emailed after `signup` and receive the access token for this MCP server. **Returns**: `access_token` (a Bearer token for this server, valid for `expires_in` seconds), `organisation_id`, and `user_id`. For an address that already had an account, the token belongs to that account's existing workspace; a workspace that was never prepared is prepared now. Reconnect to this MCP server sending "Authorization: Bearer <access_token>" on every request. Then call `verify_connection` and `get_activation_status` and follow its `nextActions` to finish onboarding. The token is not refreshable: when it expires, call `signup` and `verify_email` again. **Errors**: `confirmation_expired` means the code is too old (call `signup` again); `confirmation_failed` means it did not match; `workspace_unavailable` means the code was accepted but the workspace could not be prepared (call `signup` again for a new code, never `verify_email` with the used one).

  ConnectorOAuth

• verify_emailA

  mcpA

  Confirm the code Aient emailed after `signup` and receive the access token for this MCP server. **Returns**: `access_token` (a Bearer token for this server, valid for `expires_in` seconds), `organisation_id`, and `user_id`. For an address that already had an account, the token belongs to that account's existing workspace; a workspace that was never prepared is prepared now. Reconnect to this MCP server sending "Authorization: Bearer <access_token>" on every request. Then call `verify_connection` and `get_activation_status` and follow its `nextActions` to finish onboarding. The token is not refreshable: when it expires, call `signup` and `verify_email` again. **Errors**: `confirmation_expired` means the code is too old (call `signup` again); `confirmation_failed` means it did not match; `workspace_unavailable` means the code was accepted but the workspace could not be prepared (call `signup` again for a new code, never `verify_email` with the used one).

  ConnectorOAuth

• arroway_rememberA

  ArrowayA

  Save a durable memory (decision/rule/fact/preference/reference/identity) as governed by default. For a source-backed fact or reference that is useful only as agent context, set treatment='finding' and explain why: it costs nobody a review, and is stored as CONTEXT, never a human-sanctioned norm, cannot be pinned, and is shown separately in Findings. A finding cannot replace a sanctioned memory; correcting another finding is in-place replacement with no human queue. A finding a person revoked cannot be written again unless they reconsidered in this conversation — related_checked does not unlock that. 'identity' is WHO someone is — a person, a relation, a background: it never expires, never pins by default, and comes back when the person is part of the task; someone from the user's own circle belongs in their personal project, people of a business in that business's project. If the human explicitly stated or sanctioned it in this conversation, set decided_by_human=true (memory becomes active). Otherwise it is saved as a PROPOSAL for the human's weekly review — never present a proposal as a decision. kill_condition is mandatory: what would kill or force a review of this memory. A RULE takes TWO calls: send it with no pin fields and no related_checked, read the neighbours and the block cost the server returns, then call again with the token it gave you and the pin decided against what you just saw. Any OTHER type stays one call unless you ask to pin it: sending pin_suggested or pin_requested_by_human starts the same comparison, and only the second call with the returned token can pin it. Any type that the server stops for strong related memories also takes TWO calls: read those memories, then return related_checked=true together with its related_check_token. A flag alone never proves a comparison happened.

  ConnectorOAuth

• arroway_rememberA

  ArrowayA

  Save a durable memory (decision/rule/fact/preference/reference/identity) as governed by default. For a source-backed fact or reference that is useful only as agent context, set treatment='finding' and explain why: it costs nobody a review, and is stored as CONTEXT, never a human-sanctioned norm, cannot be pinned, and is shown separately in Findings. A finding cannot replace a sanctioned memory; correcting another finding is in-place replacement with no human queue. A finding a person revoked cannot be written again unless they reconsidered in this conversation — related_checked does not unlock that. 'identity' is WHO someone is — a person, a relation, a background: it never expires, never pins by default, and comes back when the person is part of the task; someone from the user's own circle belongs in their personal project, people of a business in that business's project. If the human explicitly stated or sanctioned it in this conversation, set decided_by_human=true (memory becomes active). Otherwise it is saved as a PROPOSAL for the human's weekly review — never present a proposal as a decision. kill_condition is mandatory: what would kill or force a review of this memory. A RULE takes TWO calls: send it with no pin fields and no related_checked, read the neighbours and the block cost the server returns, then call again with the token it gave you and the pin decided against what you just saw. Any OTHER type stays one call unless you ask to pin it: sending pin_suggested or pin_requested_by_human starts the same comparison, and only the second call with the returned token can pin it. Any type that the server stops for strong related memories also takes TWO calls: read those memories, then return related_checked=true together with its related_check_token. A flag alone never proves a comparison happened.

  ConnectorOAuth

• web_search_exaA

  exaA

  Search the web for any topic and get clean, ready-to-use content. Best for: Finding current information, news, facts, people, companies, or answering questions about any topic. Returns: Clean text content from top search results. Query tips: describe the ideal page, not keywords. "blog post comparing React and Vue performance" not "React vs Vue". Use category:people / category:company to search through Linkedin profiles / companies respectively. If highlights are insufficient, follow up with web_fetch_exa on the best URLs.

  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

• general_searchA

  NansenA

  General search tool. This is your FIRST entry point to look up for possible tokens, entities, and addresses related to a query. Do NOT use this tool for prediction markets. For Polymarket names, topics, event slugs, or URLs, use `prediction_market_lookup` instead. Nansen MCP does not support NFTs, however check using this tool if the query relates to a token. Regular tokens and NFTs can have the same name. This tool allows you to: - Check if a (fungible) token exists by name, symbol, or contract address - Search information about a token - Current price in USD - Trading volume - Contract address and chain information - Market cap and supply data when available - Search information about an entity - Find the address behind a Nansen label (public figure, fund, exchange wallet) - Find Nansen labels of an address (EOA) or resolve a domain (.eth, .sol)

  ConnectorNo auth