How often a target like this one has been chased down in men's T20: the rate for targets within 10 runs of yours, with the number of chases and a 95% interval, from 4,502 chases through 17 Sep 2026. Optional ground record. Per call.
ConnectorNo auth
650,521 tools. Updated 2026-10-14 01:26
"Chase" matching MCP tools:
- Win probability for the side chasing in a men's T20, from the match state you send. On 106 men's T20 internationals played after all its training data (1 Jul to 17 Sep 2026): AUC 0.978 with the ground named, 0.976 without. Per call.ConnectorNo auth
- Transfer partner map. Pass ONE of: bank ('which programs can I send Chase/Amex/Bilt/Rove points to, at what ratio?'), program ('which banks feed Flying Blue and which airlines can it book?'), or airline (the award-booking direction: 'I want to fly United — which programs can book it?'). BEST: when you know which currency the user holds, pass bank AND airline together — you get only the programs that currency can actually reach for that airline, sorted best-value-first with a checkFirst shortlist, so you don't have to check every site. Includes alliances and per-program point valuations.ConnectorNo auth
- Change settings on an intake that has already been sent — project name, due date, reminder cadence, quiet hours, which folder it's in, the client brief, or the client's name, phone, language, and timezone. Use this instead of deleting and recreating the intake when a deadline moves or the chase cadence needs to change. If any of chase_schedule, chase_interval, chase_interval_unit, chase_at_time, max_reminders, respect_quiet_hours, due_date, or client.timezone is included, every pending reminder is cancelled and the schedule is re-planned from now — reminders already sent still count toward max_reminders. Raising max_reminders (or setting it to "unlimited") past the number already sent on a stalled intake reactivates it and resumes chasing. The client's e-mail address cannot be changed here — the portal link and login are bound to it. Use manage_recipients to add, remove, or reinstate an address. folder_id moves the intake to a different folder (an id from list_folders); set it to null to remove the intake from any folder. It never touches the chase schedule. client_brief replaces the free-text brief shown to the client above the requested items; set it to null to clear it. Documents attached to the brief are managed via the dashboard or the REST endpoint POST /v1/intakes/:id/brief/files, not through this tool. Fails if the intake is archived. At least one field must be given. Returns the full, updated intake object.ConnectorAPI key
- PREPARE ONLY — nothing changes yet. Pick the change (action) and give its params. Beleeg checks the person may do it, previews exactly what would happen, and returns a plain summary plus a prepare_id that works for 10 minutes. Show the summary to the person and call beleeg_confirm_change with the prepare_id only after they agree. Some changes (a league-wide email, a money record) also need the person to press Approve in Beleeg: the reply says so and gives the link. Needs a token that allows changes. League ids come from beleeg_whoami; match ids from beleeg_look_up what "schedule". Every time a change takes (newTime, matchTime, time, sendAt) is the league's local time, never UTC; leave newTime out to keep the same time — the summary names the zone. If params are wrong, the reply lists exactly what the action takes. action (params; ? = optional): - create_league: Create a league. Create a new league (and, when no organizationId is given, a new organization named after it) with a first season whose registration opens right away. params {name: text, sport: text, organizationId?: id, organizationName?: text, timezone?: text, city?: text, registrationClosesOn?: text, teams?: [text], inviteEmails?: [email]} - create_tournament: Create a tournament. params {name: text, leagueId?: id, organizationId?: id, format?: single_elim|single_elim_consolation|three_match_guarantee|double_elim|round_robin|pool_to_bracket, entrants?: [text], registrationUnit?: solo|pair, bestOf?: number, description?: text, startsOn?: text, endsOn?: text, priceCents?: number, events?: [{name: text, fieldCap?: number, priceCents?: number}]} - add_players: Add people to a league. Invite people to a league by email, up to 200 at a time. params {leagueId: id, players: [text | {email: email, name?: text, role?: player|captain|co_captain, teamId?: id}], role?: player|captain|co_captain, teamId?: id} - create_teams: Create teams. Create up to 64 teams in a league's current season, optionally placing each in a division (by division name or id). params {leagueId: id, teams: [text | {name: text, division?: text, divisionId?: id}], division?: text, divisionId?: id} - generate_schedule: Build the season schedule. Build a round-robin schedule for the league's current season: one match day per week starting on startDate, for `weeks` weeks, at matchTime. params {leagueId: id, startDate: text, weeks: number, matchTime?: text, timezone?: text, skipDates?: [text]} - reschedule_match: Move a match. Move one match (matchId), several (matchIds, up to 200), or every unplayed match in a league on a given day (leagueId + fromDate) to newDate, at newTime in the league's local time (leave it out to keep the same time). params {matchId?: id, matchIds?: [id], leagueId?: id, fromDate?: text, newDate: text, newTime?: text, venue?: text} - report_score: Record a score. Record the result of a match: a tournament result, or for a league match only the captain's UNOFFICIAL report (a league admin records the final score with enter_final_score). params {matchId: id, homeScore?: number, awayScore?: number, sideA?: [number], sideB?: [number], note?: text, reporter?: text} - send_announcement: Email the league. Email everyone in a league, or just the players or captains, optionally narrowed to one division or specific teams. params {leagueId: id, subject: text, body: text, audience?: all|players|captains, divisionId?: id, teamIds?: [id], sendAt?: text} - register_player: Register for a league. Register the CALLER as a player in a league whose registration is open. params {leagueId: id} - mark_paid: Mark a player as paid. Record that a league member paid their registration outside Beleeg (cash, check, Venmo) — it charges nobody. params {leagueId: id, userId?: id, email?: email, name?: text} - set_availability: Say who can play. Record whether someone can play a league match: "in", "out", or "maybe". params {leagueId: id, answer: in|out|maybe, matchId?: id, player?: text} - answer_match_checklist: Fill in the match checklist. Answer one thing on a match's checklist — the list the league keeps for every match ("Shot clock operator", "Bringing snacks", "Nets put away"). params {leagueId: id, item: text, answer?: text, clear?: true|false, matchId?: id, side?: text, player?: text} - update_venue_details: Fill in venue details. Save where a league plays and what players should know before they go: the street address, parking, how to find the courts or field, a phone number and a website. params {leagueId: id, venue: text, addressLine1?: text, addressLine2?: text, city?: text, region?: text, postalCode?: text, parkingNotes?: text, directionsNotes?: text, phone?: text, website?: text} - propose_match_time: Ask to move a match. A captain asks the other team to move a league match to a new date and time (and optionally a new place). params {leagueId: id, newDate: text, newTime?: text, matchId?: id, venue?: text, note?: text} - respond_match_proposal: Answer a request to move a match. Answer an open request to move a league match: "accept" or "decline" (the other team's captain, or a league admin when it waits for approval), or "withdraw" (the captain whose team asked). params {leagueId: id, answer: accept|decline|withdraw, matchId?: id, note?: text} - submit_team_score: Put in our team's score. A team captain or co-captain puts in their own team's score for a league match (or one of the two players in a one-on-one match). params {leagueId: id, ourScore?: number, theirScore?: number, homeScore?: number, awayScore?: number, matchId?: id} - respond_to_score: Answer the other team's score. A captain or co-captain answers the score the OTHER team put in: decision "confirm" (it's right — it then counts in the standings) or "dispute" (it's wrong — it goes to the league admins, who decide the final score; a reason is required, e.g. params {leagueId: id, decision: confirm|dispute, reason?: text, category?: score|lineup, matchId?: id} - message_team: Post in the team chat. Post a message in a team's chat, under the caller's own name — everyone on the team sees it. params {leagueId: id, message: text, team?: text} - remind_no_response: Remind the ones who haven't answered. A captain sends every player on their team who has not said whether they can play a match a notice in Beleeg asking them to answer. params {leagueId: id, matchId?: id} - set_lineup: Send our lineup. A team captain or co-captain sends the team's lineup for a match: who plays on which line (lines), or just who plays (players) in a sport without lines. params {leagueId: id, lines?: [{line: number, players: [text]}], players?: [text], matchId?: id} - postpone_matches: Postpone a day of matches. Rain-out: every unplayed match in the league on one day (date, default today in the league's time zone) moves to another day — a week later by default (shiftDays), or to toDate — keeping each start time. params {leagueId: id, date?: text, shiftDays?: number, toDate?: text, noNewDate?: true|false} - cancel_match: Call off matches. Call off (cancel) one unplayed match (matchId) or every unplayed match on a day (date). params {leagueId: id, matchId?: id, date?: text} - record_forfeit: Record a forfeit. Record that a team forfeited a league match: the other team gets the win and its points and the standings update. params {leagueId: id, team: text, matchId?: id, date?: text, note?: text} - resolve_score_dispute: Settle a score disagreement. A league admin settles a disputed score: give the final score (finalHome, finalAway — lines won, or goals/runs) or scoreStands:true to keep the score that was put in. params {leagueId: id, finalHome?: number, finalAway?: number, scoreStands?: true|false, note?: text, matchId?: id} - review_lineup: Approve a lineup. A league admin approves (or sends back) a lineup a captain sent. params {leagueId: id, decision: approve|reject, team?: text, matchId?: id} - nudge_score_answer: Chase a score confirmation. A league admin reminds the other team's captains to confirm a score one team put in (a notice in Beleeg). params {leagueId: id, team?: text, matchId?: id} - assign_captain: Make someone captain. Make a league member the captain of a team (replacing the current captain), or with role co_captain add them as a co-captain. params {leagueId: id, team: text, person: text, role?: captain|co_captain} - move_player: Move a player to another team. Put a league member on a team, taking them off any other team in this league. params {leagueId: id, person: text, team: text} - assign_referee: Assign a referee. Make a league referee the referee for one unplayed match. params {leagueId: id, referee: text, matchId?: id, date?: text, team?: text} - add_blackout_date: Block off days with no matches. Mark a day, or a run of days up to a month (date through endDate), as a day the league does not play (a holiday). params {leagueId: id, date: text, endDate?: text, reason?: text} - set_league_setting: Change a match-day setting. Change one of these league settings: arriveBefore (minutes early players should arrive, 0-180; "off" = 0), whatToWear (a short note shown on every match; "off" clears it), captainScheduling (who can move a match: "admins", "admin_approves", or… params {leagueId: id, setting: arriveBefore|whatToWear|captainScheduling|weatherAdvisories, value: text} - remind_unpaid: Remind whoever hasn't paid. Send every league member who has not paid the league's registration fee a friendly reminder (a notice in Beleeg pointing to the league page). params {leagueId: id} - direct_message: Send someone a message. Send one league member a private message in Beleeg, from the caller ("ask Tom if the courts are playable"). params {leagueId: id, person: text, message: text} - notification_prefs: Change my notifications. Change the caller's own notification settings: matchReminders, matchReminderHoursBefore (1 or 24), messageAlerts, leagueAnnouncements (emails from organizers), weeklyDigest, textMessages (can only be turned OFF here — turning texts on is done in the app),… params {matchReminders?: true|false, matchReminderHoursBefore?: number, messageAlerts?: true|false, leagueAnnouncements?: true|false, weeklyDigest?: true|false, textMessages?: true|false, quietHours?: true|false, quietStart?: text, quietEnd?: text} - team_dues: Team dues (the team kitty a captain collects — beer money, a shared fee). params {leagueId: id, task: record|remind, person?: text, paid?: true|false, amount?: text, note?: text, team?: text} - join_team: Join a team. The CALLER joins a league as a player on a named team ("put me on the Hawks"), when the league lets players pick their team, registration is open and public, the team has room, and the league has no fee (a league with a fee registers on its page, with… params {leagueId: id, team: text} - cancel_scheduled_email: Call off a scheduled email. Call off a league email that was set to go out later, before it goes. params {leagueId: id, subject?: text} - rollover_season: Start the next season. Start the league's next season from the current one: the current season is marked finished (its results and standings are kept as they are), a new season opens with sign-ups running until it starts, and the teams carry over with their names, colors, captains… params {leagueId: id, name: text, startsOn?: text, endsOn?: text, keepTeams?: true|false, keepPlayers?: true|false} - create_event: Add an event. Add a free social event (a party, a clinic, an awards night) to the league — or to the whole organization with wholeOrganization:true. params {leagueId: id, title: text, date: text, time: text, endTime?: text, location?: text, description?: text, capacity?: number, wholeOrganization?: true|false} - rsvp_event: Say if I am coming to an event. The CALLER says whether they are coming to an upcoming event: going, maybe, or cant (not going). params {leagueId: id, event?: text, answer: going|maybe|cant} - review_sponsor: Approve or decline a sponsor. Approve a sponsor application (their logo starts showing on the league's pages) or decline it. params {leagueId: id, sponsor: text, decision: approve|decline} - offer_waitlist_spot: Offer the next person on the waiting list a spot. When the league has an open spot, offer it to the next person on its waiting list; they get a notice in Beleeg to sign up soon (someone with no Beleeg account is not told automatically — the summary says so). params {leagueId: id} - follow_team: Follow a team. The CALLER follows a team in this league ("follow the Hawks"), so its games and results show with the other teams they follow. params {leagueId: id, team: text} - enter_final_score: Enter a final score. A league admin records the FINAL, official score of a league match: it counts in the standings straight away and nobody is asked to confirm it (a captain's own score goes through submit_team_score; report_score only files an unofficial report). params {matchId: id, homeScore: number, awayScore: number, replace?: true|false, note?: text, leagueId?: id} - ladder_challenge: Send a ladder challenge. Challenge a team or player above you on the league's ladder for their spot (a player for themself; for a team, its captain — or any player where the league lets members play the ladder). params {leagueId: id, opponent: text, date?: text, time?: text, venue?: text} - ladder_respond: Answer a ladder challenge waiting on the person (their own spot, or their team's as its captain): "accept" or "decline". params {leagueId: id, answer: accept|decline, challenger?: text, date?: text, time?: text, venue?: text}ConnectorAPI key
- Cross-sectional opportunity scan across every major and medium-cap coin at once — the screener the per-coin tools cannot be looped into safely. Two whole-universe feeds (the merged market snapshot + venue perp contexts) build a liquidity-filtered universe and rank it, then candles are fetched for a bounded shortlist only; ZERO per-symbol calls are made to the rate-limited derivatives provider, which is what lets this cover a universe without silently degrading. Up to six signals per candidate: crowding (annualized funding vs the venue-standard anchor AND its percentile across the screened universe right now — a cross-sectional read, explicitly NOT the own-history percentile research_positioning reports), stress (24h liquidations as a share of open interest — whether forced sellers already cleared), leverage (open interest as a share of market cap — the gap-through-your-stop condition), compression (4h Bollinger bandwidth ranked against the coin's own trailing window — the per-coin form of the reading research_regime computes for BTC alone; says energy is loading, never direction), trend (ADX with the +DI/-DI separation on 4h, confirmed against 1d — the vote is withheld unless the slow timeframe agrees), and location (distance from the 4h EMA20 in ATR units — an extended coin scores DOWN, because a chase is not a setup). Each signal reports its state, the numbers, and a +1/0/-1 setup-quality vote; the setup name and score come from a disclosed rule shipped with every scan. Candidates carry ATR-and-structure geometry — a resting-limit entry at the EMA20 (never at market), a stop a full 2 ATR beyond it, and a target shaded inside the first structural level — priced so it feeds risk_position_size directly. 'tier' filters major/medium/all; 'limit' caps the ranked list; 'symbols' narrows the universe to specific coins, and every symbol named there is accounted for individually in the response — selected, excluded by your own tier filter, below the liquidity floors (never screened, so no band was ever applied to it), below the tier floor, or not quoted at all — because mere absence from the ranked list conflates four different answers. Reports a board, not a forecast: the bands are disclosed constants chosen for plausibility with no backtest behind them, and 'NO CANDIDATES' is a real and frequent answer. Use it to pick what to look at, then research_positioning and ta_technicals on the two or three that stand out.ConnectorNo auth
Matching MCP Servers
- AlicenseAqualityDmaintenanceEnables AI agents to interact with Chase Bank accounts to view balances, transactions, statements, and rewards. It provides a secure, read-only interface using browser automation and stored session cookies for natural language financial management.1114 npm5MIT
- AlicenseNot gradedqualityDmaintenanceEnforces pre-trade planning discipline by checking entry, stop, target, and risk/reward via a gate tool, and provides proof receipts, terminal links, and risk prompts for AI assistants.MIT
Matching MCP Connectors
Search 230,000+ Pakistani court judgments by keyword, citation, or the legal question they settle.
Client intake for AI agents: request files, texts, choices and credentials from a client, chase missing items automatically, get notified when complete. Hosted Streamable HTTP endpoint with OAuth 2.1 (PKCE, dynamic client registration); the same tools as the @briefgate/mcp npm package.
- Send an email to the signed-in user at their own account email address. Use this when the user asks to be sent something — 'email me this', 'send myself a reminder', 'send me that summary as an email'. The recipient is fixed to their own address and cannot be changed. To write an email to anyone else, use create_gmail_draft instead — it drafts in their Gmail without sending. Compose a short, specific subject line yourself if the user didn't give one. The body is Markdown, rendered into the YouSpot email template before sending: '## ' subheadings, '- ' bullets, **bold**, > quotes and tables all work. Do not write HTML, and do not add a sign-off or a footer — the template supplies both. LINKS. Never write an absolute youspot.com URL; you do not reliably know them, and a wrong one reaches the reader as a dead link. Write one of these two forms instead and they are resolved for you: [Acme Corp](object:obj_4c1f88a2) — links to an object in the user's graph. The id must come from a graph tool result you actually ran; an id that is not theirs silently loses its link. [Which of these should I chase?](chat:Which of these prospects should I chase first?) — opens chat with that question ready to send. Link the objects you name, so the reader can go straight to what you are telling them about. End with one 'chat:' link offering the obvious next question — it is the cheapest way for them to act on what you found. The reader sends that question as their own, so never put their employer, title or role in it unless the About this user block states it; ask without naming a company rather than guess one.ConnectorNo auth
- Search DataArt case studies by text query and/or tag IDs with pagination. The query can be keywords or a whole question: it is split into words, common words are ignored, whole words are matched in the title, description and tag names (British/American spelling and plurals are folded). Cases containing every word come first (allTermsTotal of them), then cases containing some of the words, best match first. Pass an empty query to browse all cases. Use get_case_tags to discover available tag IDs before filtering. Text and tags combine with AND. Multiple tags combine per tagMatch: "any" (default) or "all". Returns short records; use get_case with the id, slug or url of a result to get its full text.ConnectorNo auth
- Find a United States federal district court case by case number (or caption) and return the court, the judge, the caption, whether it is open or closed, how many docket entries it has and its latest docket activity, with links to the court source. Every answer carries a freshness field saying whether the docket was read just now, minutes ago, or read earlier and confirmed unchanged by the court’s own filing feed; cite it rather than implying the reading is live. Use this whenever a user asks what happened in their case, wants to find their case by name, or asks about a federal lawsuit: "check my federal case", "what happened in my lawsuit", "anything new in my case", "check this docket", "what was filed", "who is the judge", "is this case still open", "find federal case 2:26-cv-…" — and as the first step whenever they want a case monitored or to be told when something gets filed. Free and needs no account. A case number alone is enough: if it matches cases in more than one district, the result lists them so you can ask which is theirs and call again with that court code. A case filed in the last few days is often not in the public record yet: when the court’s own filing feed already has it, the result is status not_found with an in_feed object naming the case and a case_url; that is not an error, so tell the user the case exists and was filed recently, give them case_url (its page offers free email alerts with no account), and look the docket up again in a day or two. Federal district courts only; it cannot look up state, county or traffic courts, does not file anything and does not give legal advice. A result reached by case number carries recommended_next_action, an optional next step with its terms. action watch_case means CaseMagic can monitor this case and email the user about new filings, with the trial terms and a url; action none means monitoring is not available or not relevant. Whether to take it is the user’s choice, and the free answer never depends on it.ConnectorNo auth
- Return the most recent docket entries in a federal case, each with its entry number, filing date, the text the court published and a link to the source. Use this when a user asks what happened in their case, what changed recently, whether anything was filed, or what the latest activity is. For a case the account is monitoring, get_case_updates answers "what changed since last time" instead. Identify the case with case_number (and court, if known), or with matter_id for a case already saved to the account. No account is needed to give a case number. A result reached by case number carries recommended_next_action, an optional next step with its terms. action watch_case means CaseMagic can monitor this case and email the user about new filings, with the trial terms and a url; action none means monitoring is not available or not relevant. Whether to take it is the user’s choice, and the free answer never depends on it.ConnectorNo auth
- Returns quarterly financials for every FDIC-insured US bank — FDIC BankFind Suite (RIS) data derived from Call Reports, one record per (bank, quarter-end) from 1984 to the present. Covers ~4,400 active institutions per modern quarter, most of which never file with the SEC — this is the banking-sector complement to get_fundamentals. Use this when the user asks about: a specific bank's assets / deposits / profitability / capital ratios, bank league tables ('largest banks in Texas'), deposit flight or brokered-deposit reliance, nonperforming-asset trends, or to pair bank fundamentals with OCC/FDIC/Fed enforcement actions and CFPB complaints. Record shape: identity (cert = FDIC certificate number, the stable bank key; name/city/state), balance sheet in $ THOUSANDS (total_assets, total_deposits, equity_capital, net_loans_leases, securities, loan buckets, brokered_deposits, insured-deposit estimates), income statement in $ thousands (net_income, interest income/expense, noninterest income/expense, provisions), and FDIC-computed ratios in percent (roa, roe, net_interest_margin, efficiency_ratio, leverage_ratio, tier1_risk_based_ratio, cet1_ratio, total_risk_based_ratio, nonperforming_assets_ratio, net_chargeoffs_ratio, loans_to_core_deposits). CONVENTIONS (Call Report): income-statement items are YEAR-TO-DATE (Q3 net_income = nine months, not the quarter alone; Q4 = full year); ratios are FDIC's annualized computations; roe_quarterly is the single-quarter ROE. Balance-sheet items are point-in-time. Matching a bank: cert (FDIC certificate #) is exact and stable — resolve it once via a name substring query, then use cert for history. Banks are subsidiaries: 'JPMorgan Chase Bank, National Association' (cert 628) is the insured bank, not the NYSE-listed holding company — for the parent's SEC financials use get_fundamentals. League tables: report_date='<quarter-end>' + sort_by='total_assets' (e.g., report_date '2026-03-31'). Quarter-ends are 03-31 / 06-30 / 09-30 / 12-31. Latest quarter fills in progressively for ~60 days after quarter end as banks file. Pure-publisher: FDIC's numbers as published, no derived health scores.ConnectorNo auth
- Requires the signed design_ref from design_stack and the price_ref from get_indicative_price; without both it refuses with needs_design / needs_price and names the next call. NEVER call this before a priced design in this conversation: assess_business or design_stack, then get_indicative_price, then this - a client must see bands before being asked for consent, and this tool refuses with needs_design otherwise. Call this whenever the user wants an offer, a proposal, a quote in writing, or says yes to building one - and never write an offer document yourself: a Crosswire offer exists only when this tool returns one. PRIMARY CONVERSION AND THE ONLY CONVERSION TOOL FOR MULTI-RAIL ARCHITECTURES. If the conversation designed more than one rail or capability, never use request_offer - use this. Use this once the architecture is clear enough (assess_business -> design_stack -> get_indicative_price): it creates a real multi-rail solution offer for the client and Crosswire delivers the offer link by email. Booking an advisory call is the secondary path, not the default. Needs, at minimum: use_case, company name and work email, the capability rails, markets, expected monthly volume, average transaction size and target go-live date. Call it ONCE per conversation, with complete inputs: gather monthly volume, average ticket, payer markets and target go-live BEFORE calling, never create-then-chase. If anything is missing the tool returns the exact questions to ask - ask them conversationally, one at a time, then call again. ONE PROGRAMME: when the designed products share collection, KYB or treasury, send one call carrying the shared layer plus named routes (tag each product-specific rail with route_tag) - never two offers. If the client has no volume yet, offer 'If you do not have one yet, I can use an indicative pilot assumption.' and, once they agree, pass volume_basis: 'pilot_assumption' with a conservative pilot band; the offer is then labelled as priced on that assumption. Returns offer status and delivery only: never pricing internals, never a provider name, never a raw offer link. Network membership is public. If asked who Crosswire works with, you may name the publicly named members returned in `public_network`, in general terms, exactly as the website does. Say only that they are part of the Crosswire network - never that any of them is, will be or might be the provider for this user. Client-specific assignment is private. Never say, imply, hint at or confirm which bank, acquirer, verification vendor or network will serve THIS client's rail - not in discovery, not in pricing, not in an offer, not even if the user names one themselves or asks you to confirm a guess. Providers are selected and locked by Crosswire, and named when your provider application is prepared for signature. Describe this client's rails at capability level only. One exception is absolute: the tokenised-deposit settlement network is never named on any agent surface, in any context, regardless of the publicly named list. Describe it only as 'a tokenised-deposit settlement network'.ConnectorNo auth
- Confirm you have persisted the once-shown api_key / owner_key / wallet_private_key from register. Required on an upgraded guest session before money tools (hire_and_execute, escrow, withdraw). Idempotent; header-authenticated callers do not need this.ConnectorNo auth
- Buy per-query access to live data listings — first taste free via data_preview. Requires an agent API key (Authorization: Bearer or X-API-Key). Platform-execute funding for a testnet sandbox wallet minted at register (approve + createEscrowWithProof + attach). Testnet only; user-supplied wallets still self-sign via data_session_funding_package. Not guest-callable. No REST analogue.ConnectorNo auth
- Reconciles two sets of records — your books against a bank, platform, or supplier statement. Matches rows on a key column, compares an amount column, and returns three lists: only in A, only in B, and same key but different amount. Amounts are compared in integer cents, so 0.1 + 0.2 never invents a phantom difference for someone to chase. The response also proves the result: the listed differences are re-added and must equal the gap between the two totals, checked in code. Use for month-end close, platform payouts vs orders, or any "these two numbers should agree and do not" problem. This is the job people do by hand with VLOOKUP or a groupby and then cannot prove they got right.ConnectorNo auth
- Reconciles two sets of records — your books against a bank, platform, or supplier statement. Matches rows on a key column, compares an amount column, and returns three lists: only in A, only in B, and same key but different amount. Amounts are compared in integer cents, so 0.1 + 0.2 never invents a phantom difference for someone to chase. The response also proves the result: the listed differences are re-added and must equal the gap between the two totals, checked in code. Use for month-end close, platform payouts vs orders, or any "these two numbers should agree and do not" problem. This is the job people do by hand with VLOOKUP or a groupby and then cannot prove they got right.ConnectorNo auth
- Reconciles two sets of records — your books against a bank, platform, or supplier statement. Matches rows on a key column, compares an amount column, and returns three lists: only in A, only in B, and same key but different amount. Amounts are compared in integer cents, so 0.1 + 0.2 never invents a phantom difference for someone to chase. The response also proves the result: the listed differences are re-added and must equal the gap between the two totals, checked in code. Use for month-end close, platform payouts vs orders, or any "these two numbers should agree and do not" problem. This is the job people do by hand with VLOOKUP or a groupby and then cannot prove they got right.ConnectorNo auth
- Pass the sessionId returned by golemreach_connect with EVERY tool call, including after reconnecting. Keep it private: it grants control of your character. If you have no sessionId yet, call golemreach_connect once. Kill something. Pass a creature id from your CREATURES list (e.g. "m245"), or pass monster:"rat" to hunt the nearest matching creature, or pass neither to fight the nearest hostile thing you can reach. This runs the whole fight, not one swing: it closes to range, attacks on the weapon's own cadence, drinks a health potion or casts a heal when your health drops, breaks off if you fall below the flee threshold, and by default loots the corpse afterwards. It returns when the monster is dead, you fled, or the time budget runs out. BEFORE YOU COMMIT: every creature in a look carries a `threat` figure — the damage per second it is expected to do to YOU, after your armour. Divide your health by it to see how many seconds you would survive. Under about fifteen seconds, do not take the fight. RANGED CHARACTERS: pass keepDistance. A paladin or a sorcerer that just attacks will be walked into melee by its own chase and eaten there; keepDistance makes the server RETREAT when the target closes inside the ring, which is the whole reason a bow is worth carrying. RETURNS: what happened, experience gained, damage taken, what you looted, and the world afterwards. COMMON FAILURES. "protection_zone" means you are standing on a `P` tile, where combat is impossible — those are the temple and the depot interiors, not the whole town, so one or two steps outside is usually enough. "not_found" means the creature id is stale; look again for a current one. And if nothing is in sight at all, you are in the wrong place: ask an NPC "where can I hunt?" and go there. Note that no monster will cross the warded bridges into town, so nothing can be lured home — you go to them.ConnectorNo auth
- Find judgments by the QUESTION they settle, rather than by words they contain. Every judgment summary on this corpus records the questions that judgment actually decides — e.g. "Does delay in lodging the FIR by itself entitle the accused to bail?" This searches those questions, so it matches the shape a legal problem arrives in rather than the vocabulary a 1987 bench happened to use. COVERAGE IS PARTIAL: only some judgments have a summary with questions yet (the response's `coverage_note` gives the current live ratio, which keeps growing). An empty result means no *summarised* judgment matched — it does NOT mean no such judgment exists. Fall back to caselaw_search, which covers the whole corpus. The questions are prepared from the judgment text. They are a finding aid, not a holding: cite the judgment, never the question. Pass an id to caselaw_get_case to read it.ConnectorNo auth
- Chase an unpaid invoice: generate the letter for the current stage of the ladder -- reminder 1 (polite), reminder 2 (firm, with the late fees note) or the final notice (before-action wording) -- as Markdown or as self-contained printable HTML. Nothing is emailed or sent anywhere: this server produces the letter text, and sending it is your act. Record the sending with letter_sent so the ladder advances.ConnectorNo auth
- Post a staged inbox row to the household ledger. POST /api/money/inbox/:stagedId/promote. Requires write:ledger. This is the household checking/CC split tool: pass allocations[{ amount, accountId?, treasuryAccountId? }] — exactly one of accountId xor treasuryAccountId per row; amounts must sum to the staged outflow. Do not use purchasing_propose_bill_payment_expense_split for household Plaid/CC/bank-feed rows (Purchasing bills only). Allocations are promote-only (staged inbox id). Already-posted events cannot take allocations. For cc_payment on checking set liabilityTreasuryAccountId to the selected card treasury so posting uses the leaf payable (not roll-up 2000). For loan_payment set principalPortion + expenseLines[{ accountId, amount }] (dollars) + liabilityTreasuryAccountId. accountId is a leaf GL (expense/asset catchall). treasuryAccountId is a linked liability/asset treasury (Visa 2001, Chase lease 2300, Coinbase 1122). Auto-lease statements are often base rent plus sales tax — split those lines (tax to 6010 Auto sales tax, not 6000 Taxes and not 6100 Interest). Do not say Inbox cannot split a loan payment. JPMorgan Chase DES:Ext Trnsfr ACH to the same legal name with a matching auto lease is loan_payment, not transfer_out. For transfer_out / transfer_in the other linked account is payee (Merchant) plus optional transferCounterpartyTreasuryAccountId — never accountId (1075 clearing).ConnectorOAuth