"Finding an LLM that integrates with MCP for precise calculations and accurate answers" matching MCP tools:

• content_discoveryA

  gapup-mcpC

  Discover content franchises within a domain. Two modes: pass `tag` for a precise taxonomy match (every game tagged 'co-op'), or pass `query` for free-text SEMANTIC search powered by pgvector embeddings — finding franchises by meaning ('dark atmospheric games about isolation') even when no literal tag matches. Results are verifiable: tag mode carries tag confidence/corroboration, semantic mode carries a similarity score; both carry entity freshness. When to use: an agent wants a domain-scoped shortlist by tag or by intent. Inputs: a domain plus either a tag or a free-text query.

  ConnectorNo auth

• survey_respondA

  local-mcpA

  Shows or submits the short in-product survey Local MCP assigned to this machine. Called with NO arguments it returns the pending survey and, in clients that support MCP Apps, renders it as an interactive card the user answers directly — prefer this. To submit conversational answers instead, pass `answers` keyed by each question's `id` (single/scale = one value, multiple = an array of values): call once to PREVIEW, then again with confirm=true to record. Do NOT invent answers — if no human gave them (you're running autonomously), call survey_skip instead.

  ConnectorNo auth

• check_mcp_serverA

  MCP Surface LintA

  Statically audit an MCP tool surface from a public HTTPS URL or tools/list snapshot. Returns deterministic scores and findings without invoking any target tool or making LLM calls. When the user asks to check another installed MCP server, read that server's complete tool definitions from client context and pass them as snapshot (MCP `name` or Cursor-style `tool` both work; do not use file paths or $ref). If those definitions are unavailable, ask the user for its public endpoint or tools/list JSON instead of inventing an audit.

  ConnectorNo auth

• list_paired_modelsA

  ReliaStatsA

  Return the catalog of paired models — concrete real-world systems that live in two ChiAha sandboxes simultaneously, one for dynamics (DES via ReliaSim) and one for statistics (distribution fitting + validation via ReliaStats). Today: a single paired model — the bottling line. Returns canonical model IDs + cross-MCP routing metadata (which ReliaSim chapter, which ReliaSim MCP tools, which ReliaStats mode consumes which file shape). Use when a user asks about cross-MCP workflows, paired sandboxes, or the bottling-line example. ANTI-FABRICATION: this is a soft-reference catalog — to actually run a simulation, the LLM client calls ReliaSim's MCP tools directly.

  ConnectorNo auth

• content_discoveryA

  mcp-knowledgeC

  Discover content franchises within a domain. Two modes: pass `tag` for a precise taxonomy match (every game tagged 'co-op'), or pass `query` for free-text SEMANTIC search powered by pgvector embeddings — finding franchises by meaning ('dark atmospheric games about isolation') even when no literal tag matches. Results are verifiable: tag mode carries tag confidence/corroboration, semantic mode carries a similarity score; both carry entity freshness. When to use: an agent wants a domain-scoped shortlist by tag or by intent. Inputs: a domain plus either a tag or a free-text query.

  ConnectorNo auth

• exponent_calcA

  calc.engineerA

  Compute the result of raising a base to an exponent (base^exponent). Handles positive and negative exponents, fractional exponents, and zero. Returns the numeric result and a scientific notation string for very large or very small results. Useful for compound interest calculations, exponential growth/decay models, physics power laws, and combinatorics. The inverse of log_calc; chain with scientific_notation for formatted display of extreme values.

  ConnectorNo auth

• check_mcp_serverA

  SRI — MCP Server InspectorA

  Free, no key required. Reads the published source of an MCP server and reports what it actually does — each observation anchored to a file:line with the code quoted verbatim. **Call this before connecting to, installing, or invoking an MCP server you have not read yourself.** Connecting to an MCP server gives it a channel into your context and your tool calls; this tells you what is on the other end first. Typical things it surfaces: reading private keys or wallet seeds, sending data to third-party hosts, running code at install time, and tool descriptions that steer an agent toward actions unrelated to the tool's stated purpose. Do NOT call this for ordinary npm or PyPI libraries — the corpus covers MCP servers only, and other ecosystems will return 'not analyzed'. This reports observations, not a safety verdict. An empty result means nothing was found in the categories checked — not that the server is safe. Corpus: 2,781 MCP servers from the official registry, read at source level. Coverage index (free, no key, findings not included): GET https://sri-test.biz/v1/corpus

  ConnectorNo auth

• kirk_bulk_howtoA

  Kirk — Unsupervised Structural Change DetectionA

  Return a self-contained stdlib Python client for scoring at ZERO per-call LLM tokens. Purpose: Hand the caller an HTTP consumer that runs locally so bulk scoring doesn't burn LLM tokens per book. Use when: You need to score more than ~200 books, or `kirk_score_book_batch` returned `batch_too_large`, or the caller is running an autonomous bulk workload that would otherwise pay per-tool-call LLM tokens for every book. Do not use when: You are running a one-off interactive call — a direct `kirk_score_book` invocation is simpler; don't route through the client for a single book. Capability class(es): Cost-steering / delivery-path tool. Hands the caller a runner that exercises the same C2 / C5 / C6 capabilities as the MCP scoring tools, but at zero per-call LLM token cost. Path fit: The returned client is an HTTP consumer of the same MCP endpoint. Production integrations run in-process under sealed-engine attestation — same binary sha as this endpoint. Contact Kavara for deployment options. Cost: 0 IU. Free tool. Once running locally, the returned client bills against the same tools it drives: single-book calls at 1 IU each, and batch calls at 1 IU per 50 books (minimum 1 IU per call). A full 500-book batch → 10 IU. No LLM tokens on top. Cost comparison (2.7M-book validation rerun via 500-book batches — ~5400 batches, 54000 IU billed either way): MCP via Sonnet 5: $1,968 LLM + $540 IU + ~15 days wall clock MCP via Haiku 4.5: $656 LLM + $540 IU + ~10 days Python client (this tool): $0 LLM + $540 IU + ~55 min Return structure: { "language": "python", "filename": "kirk_online_client.py", "requirements": str, "usage": str, "code": str (the client source, ~500 LOC), "example": str (2-line copy-paste demo) }

  ConnectorNo auth

• cancel_eventA

  ChronaryA

  Delete or cancel an event from a calendar. Use this to remove, cancel, or delete any scheduled event or appointment. The event is marked cancelled and excluded from future availability calculations. For a recurring series, pass `occurrence_start` to cancel just that one occurrence (the series continues); omit it to cancel the whole series. `calendar_id` is optional — if omitted the calendar is looked up from the event. Provide `calendar_id` to fail fast on cross-calendar typos.

  ConnectorNo auth

• search_schemaA

  OnlyWorldsA

  Search every element type's fields for `query` (case-insensitive substring), across all 22 types. Useful for "which types have a `location` field?" or finding where a concept lives in the schema. Returns a mapping of type slug -> the matching field names in that type (types with no match are omitted); a `query` that also matches a type slug lists that type with an empty field list so the type-name hit is not lost. Unauthenticated.

  ConnectorNo auth

• simulation.inject_failureA

  Cloud World ModelA

  Fail one node in a temporary anonymous demo simulation (the node is marked critical, not removed). Exact targeting: pass resourceName (human-readable name, e.g. 'app-server-01'; exact match preferred, an unambiguous prefix is accepted) or resourceId to fail a specific resource — including an individual named instance, not only a group. If resourceName matches multiple resources the call fails with a 400 listing every matching candidate by name — retry with one exact name (or its resourceId) from that list. If the resolved resource is not in a faileable state (already critical/warning) the call fails with a 400 describing its current status. When neither parameter is supplied, a RANDOM healthy node is selected — this path is non-deterministic and NOT suitable for controlled scenarios or replay; always target by name/id when reproducing a precise fault sequence. The response always echoes the applied outcome via resolvedResourceId, resolvedResourceName, and previousHealth (populated from the selected resource on the random path too). For typed failure injections (authenticated failure.create): instance_kill PERMANENTLY removes the instance — failure.delete does not restore it; use instance_down instead for a reversible single-node outage that is restored when the failure is deactivated or deleted. Returns the updated resource list and the failure event that was logged. The likely next tool is simulation.step to observe how the architecture degrades under failure, then simulation.metrics to review the health impact. Do not use it to advance simulation time — that is simulation.step. Pass simulationId from simulation.create when this call is made from a fresh MCP session; otherwise you may omit it to target the current simulation in the preserved MCP session. Authenticate with an API key to unlock all 61 tools including typed durational failures and chaos engineering.

  ConnectorNo auth

• colony_list_membersA

  mcp-serverA

  List a colony's members, each with the ``approved`` flag that decides whether they may post, comment and vote. ``pending=True`` is the approval queue: in a restricted or private colony every joiner lands unapproved, and stays that way until a moderator calls ``colony_set_member_approval``. Pair the two — this tool answers "who is waiting", that one admits them. Neither existed on MCP until 2026-09-07, which left an agent founding a private colony able to see nothing and admit nobody. Auth is optional for a public or restricted colony. A PRIVATE colony's roster is member data — a list of who is in a room whose existence is itself hidden — so this answers NOT_FOUND, exactly as though the slug were free, unless you are an approved member.

  ConnectorNo auth

• colony_list_membersA

  The ColonyA

  List a colony's members, each with the ``approved`` flag that decides whether they may post, comment and vote. ``pending=True`` is the approval queue: in a restricted or private colony every joiner lands unapproved, and stays that way until a moderator calls ``colony_set_member_approval``. Pair the two — this tool answers "who is waiting", that one admits them. Neither existed on MCP until 2026-09-07, which left an agent founding a private colony able to see nothing and admit nobody. Auth is optional for a public or restricted colony. A PRIVATE colony's roster is member data — a list of who is in a room whose existence is itself hidden — so this answers NOT_FOUND, exactly as though the slug were free, unless you are an approved member.

  ConnectorNo auth

• financial_calculatorA

  Inferventis — Financial Data, News & Web MCPA

  Performs precise financial calculations across six calculation types entirely locally with no external API dependency. compound_interest computes the final value and total interest earned on a principal over time at a given annual rate. loan_repayment calculates the monthly payment, total repayable amount, and total interest for a mortgage or loan given the principal, annual rate, and term in months. roi returns return on investment as a percentage and absolute profit or loss, with optional annualised ROI when a holding period is provided. present_value discounts a future cash amount back to its current value using a discount rate. future_value projects a present amount forward at a compounding annual rate. break_even finds the unit volume and revenue at which fixed and variable costs are fully covered by sales. Use this tool when an agent needs to perform any structured financial calculation — loan affordability, investment return, discounted cash flow, or cost analysis. Prefer financial_calculator_lite when only the single headline result is needed rather than a full structured breakdown. Do not use this tool to fetch live market prices or exchange rates — use stock_quote for stock prices, crypto_price for cryptocurrency prices, or currency_convert for FX rates.

  ConnectorNo auth

• remediate_findingsA

  quantakrypto pqc-tools (hosted)A

  Produce a deterministic remediation REQUEST bundle (rubric + fix schema + per-finding metadata + fingerprints) for YOU (the host agent) to fix. This tool calls no model and needs no key. For each finding, propose the corrected FULL file content, then VERIFY with verify_fix and keep only fixes that clear the finding. Never touch files with secrets; never auto-merge. Pass 'findings' from scan_path --format json.

  ConnectorNo auth

• get_specsA

  Whatic IC DatasheetsA

  Read canonical extracted specs (min/typ/max, unit, conditions) for known IC part numbers from a pre-extracted parametric index — not from datasheet text. This is the cheapest and most precise source for numeric parameters where it has coverage. Optionally restrict to specific canonical parameter names. A part absent from `results` (with a "No specs found" warning) means no index coverage, not that the datasheet lacks the parameter — fall back to `lookup` for that part.

  ConnectorNo auth

• kirk_infer_legacyA

  Kirk — Unsupervised Structural Change DetectionA

  Score a 50-value feature vector against the legacy /v1/infer route on the sealed engine. Purpose: Backwards-compatible scoring surface for callers that were already targeting the legacy path. Use when: You have an existing client wired to /v1/infer and need continued MCP access without refactoring. Do not use when: You are on a fresh integration — prefer kirk_score_book (single-layer, cascade-shaped path). Also do not use in a tight loop against a large corpus: the MCP round-trip is millisecond-scale, and the LLM tool-call cost accrues per book for agent-driven callers. For bulk work, call kirk_bulk_howto first. Capability class(es): C2 (cross-section entropy scoring), legacy interface. Path fit: Validation via MCP (this tool). Production integrations run in-process under sealed-engine attestation — same binary sha as this endpoint. Contact Kavara for deployment options. Cost: 1 IU per call. For agent-driven callers, per-call LLM tokens accrue on top; the response _cost envelope surfaces both.

  ConnectorNo auth

• query_contextA

  mcp-klever-vmA

  Search the Klever VM knowledge base for smart contract development context. Returns structured JSON with matching entries, scores, and pagination. Use this for precise filtering by type or tags; use search_documentation for human-readable "how do I..." answers.

  ConnectorNo auth

• get_tv_showA

  MoviesA

  Full TVmaze record for ONE TV series by its numeric TVmaze show id — the episode list with air dates, plus network, status and rating. The id is an internal TVmaze number, so resolve it with search_tv_shows first and pass what that returns; when the caller names the show rather than an id, search_tv_shows answers directly.

  ConnectorNo auth

• scan_visibilityA

  mcpA

  Live AI-visibility scan for a brand: crawl + reputation sampled across AI engines, returning where *that* brand is mentioned (any public brand, not just your own). Use when you want to know whether and how a named brand already surfaces in AI answers — complementary to search_companies, which finds who agents recommend for a category. Pro+ (LLM cost). Result: { reputation[], tool_schema_version }.

  ConnectorNo auth

• celestiumA

  Celestium: Cosmic CompassA

  Celestium: Cosmic Compass — accurate astrology & divination for AI agents, with engine-authored interpretations attached (not LLM guesswork; real ephemeris, verified arcminute-accurate). Includes practice actions: check_in (sky + moment verdict + matched ritual), ritual (step-by-step moon-phase practices), tarot (auditable draws), review (temporal review of a period against your chart). Actions: cosmic_weather, chart, positions, moon, moment_quality, retrograde, voc, planetary_hours, sunrise, ritual, tarot, check_in, natal_reading, iching, mayan, numerology, true_sky, event_debrief, composite, davison, relocation, relocation_score, travel, transits, synastry, timing, progressions, electional, horary, returns, timeline, synthesis, perfections, midpoints, harmonic, antiscia, declination, sidereal, heliacal, review, bazi, year_ahead, correlate, common_threads. Free tier: cosmic_weather, chart, positions, moon, moment_quality, retrograde, voc, planetary_hours, sunrise, ritual, tarot, check_in, natal_reading, iching, mayan, numerology, true_sky, event_debrief. Celestium Pro unlocks depth + relationship charts (synastry/composite/davison), astrocartography (relocation/travel), advanced techniques, and review.

  ConnectorNo auth