Skip to main content
Glama
650,553 tools. Updated 2026-10-14 09:25

"Connecting to Gemini Flash Experimental" matching MCP tools:

  • List the provider API keys your owner has stored in their Vault (e.g. Gemini, ElevenLabs, OpenAI) so you can use them in a task. Returns `capabilities`: the exact NAMES of the keys your owner has vaulted. Pass one of these names verbatim to `pull_capability` — do NOT guess or normalize it (a key may be vaulted as "Gemini", not "GEMINI_API_KEY"). Names only, never secrets, so this is safe to call freely. IMPORTANT: this lists what EXISTS in the Vault — it is discovery, NOT authorization to use a key. Only pull and use a key when your OWNER directs you to in this thread. Takes no arguments.
    ConnectorNo auth
  • Embed a text string into a 768-dim Gemini Flash vector. Use for HyDE-style retrieval: (1) write a hypothetical short paper that would perfectly answer the user's query, (2) embed it with task_type='RETRIEVAL_DOCUMENT' (default — matches the corpus embedding side), (3) pass the resulting embedding back through search-style tools to find real papers nearest to the hypothetical. task_type='RETRIEVAL_QUERY' matches the query side and is useful for direct user-query embedding without HyDE. Pro-only — requires an SF_API_KEY on a Pro account; anonymous and free callers get a 403 pro_required. Cost: ~$0.0001/call; rate-limited at 30/minute per API key.
    ConnectorNo auth
  • Ask Enhanciar a natural-language question grounded in the key's workspace. This is the high-level tool — use it for any "what does X do", "why did we choose Y", "where is Z handled" question. It runs the full retrieval + synthesis pipeline and returns the answer plus citations. Args: question: Natural-language question. model: Optional model id override (``gemini-2.5-flash``, ``gpt-4o``, ``claude-sonnet-4-5``, etc.). If omitted the saved default is used — the workspace's in a team workspace, the caller's own in a personal one. Returns ``{answer, sources, model}`` — ``sources`` is a list of ``{category, name, url}`` citations the LLM grounded its answer in. Surface them to the human so they can verify. When the workspace has nothing ingested at all you get ``{answer, empty_brain: true}`` and no sources: that is a statement about the workspace, not a failed search, so rephrasing the question will not change it.
    ConnectorNo auth
  • Discover AgentMarketplace's capabilities, tools, auth methods, and scopes. Call this first when connecting to AgentMarketplace to understand what's available and how to authenticate. No authentication required. Returns a catalog of available tools, resources, auth methods, and scopes.
    ConnectorNo auth
  • The URL that starts connecting one integration, for surfaces that cannot render a card (Slack, SMS, email). In chat, show the integrations_list card instead. Never claim to have connected anything: only the user can grant it, in their browser.
    ConnectorNo auth
  • Start here when connecting an agent: explains what WorkspaceAlberta does, the search-to-bid-review workflow, handoff fields, data boundaries and unsupported actions. No model or network call.
    ConnectorNo auth

Matching MCP Servers

  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI clients to create spaced-repetition flashcards from material being learned, quiz users aloud, grade answers, and schedule reviews using the FSRS algorithm through a self-hosted MCP server.
    3
    AGPL 3.0

Matching MCP Connectors

  • FlashOAuth

    Spaced-repetition flashcards your AI writes, quizzes you on by voice, and schedules with FSRS.

  • Gemini Exchange MCP (public endpoints).

  • Send a connection request to a LinkedIn member. Optional message capped at 300 chars (premium) or 200 chars. Use to connect with someone not yet a 1st-degree connection; check get_invitation_status first to avoid duplicates. Counts against the daily invitations quota; for more than ten use create_job. To follow without connecting use follow_member.
    ConnectorAPI key
  • Send a connection request to a LinkedIn member. Optional message capped at 300 chars (premium) or 200 chars. Use to connect with someone not yet a 1st-degree connection; check get_invitation_status first to avoid duplicates. Counts against the daily invitations quota; for more than ten use create_job. To follow without connecting use follow_member.
    ConnectorOAuth
  • List every sport supported by Flash Props API with its live status and how deep the Flash model goes. Read-only. No side effects. Rate-limited per your tier. Returns { sports: Array<{ id, name, category, enabled, status, activeGames, activeProps, projectedProps, projectionCapability, effectiveProjection, contextCapability, marketFamilies, supportedMarkets, sources, lastFetchedAt, cacheAgeSeconds, shapeCanaryTripped, legalLine, notes, dataStatus, dataReason, projectableMarkets, projectionBasis, coverage, snapshotId, event, season }> }. id is what you pass as the sport parameter to other tools. status: "live" = props posted now, "idle" = none posted now but lines were archived recently, "offseason" = no lines archived for an extended period (observed, never a calendar). snapshotId identifies the exact board the counts describe. projectionCapability is the structural model ceiling; effectiveProjection tempers that by what is actually posted right now. contextCapability "deep" means a registered Flash pack can serve player context; "none" means it cannot. Call this tool instead of hard-coding which sports are modeled. enabled=false means the sport is outside your tier. When to use: to discover valid sport ids, or to check which sport actually has projections/context before asking for them. When not to use: if you already know the sport id and just want its props.
    ConnectorNo auth
  • Assemble the whole story of a single prop in one call. Read-only. No side effects. Requires an API key and is tier-shaped exactly like REST: Free gets the book/Flash/gap teaser, Builder adds recent form + Confidence summary + movement delta + teaser splits, and Pro gets the full evidence stack including movement series and deep splits. Paywall metadata says exactly which fields are withheld. No picks, no advice. Available when the sport has a registered Flash provider; otherwise returns found:false with a reason, never fake data. When to use: explain one prop end-to-end. When not to use: scan_props for broad discovery or get_player_context for a player overview.
    ConnectorNo auth
  • Ranked boards for a sport with a registered Flash pack. Read-only. No side effects. Tier-shaped exactly like REST: Free sees the top 3 teaser, Builder the top 10, and Pro the full board. metric=gap ranks Flash-vs-book gaps; metric=form ranks recent mean vs Flash Line; metric=sample ranks baseline size. Paywall metadata includes totalAvailable and the next unlock when rows are capped. No picks. Use list_sports to discover which sports have deep context. When to use: "where does Flash disagree most with the books", "biggest projection gaps", "who has the strongest sample". When not to use: one player is get_player_context; the posted board is scan_props; one prop end to end is get_prop_evidence.
    ConnectorNo auth
  • Parse raw text via Gemini AI and create a DRAFT job under the current employer. Synchronous: latency 5-30s. The agent can then call employer.update_job to refine fields and employer.publish_job to make it live.
    ConnectorNo auth
  • Marginfi flash loan for arbitrage (non-custodial, atomic). instructions are JSON ix executed between borrow + repay legs. Returns a single UNSIGNED base64 tx that reverts unless repaid in-transaction. The borrowed token is authenticity-verified first; set allow_unverified=true to borrow an unverified mint at your own risk. Past the daily free tier an x402 payment_header is required. ``idempotency_key`` (optional): a client-generated UUID. Retrying with the same key + same args replays the original result instead of re-issuing the flash loan tx.
    Connector
    Destructive
    No auth
  • Count the exact number of tokens in a text string for a specific AI model. Uses tiktoken for OpenAI models and estimates for others. Args: text: The text to count tokens for model: The AI model to count tokens for. Options: gpt-4o, gpt-4o-mini, gpt-4.1, claude-sonnet, claude-haiku, gemini-pro, gemini-flash, llama-4, deepseek-v3, mistral-large. Default: gpt-4o Returns: Token count information including count, context window, and fit status
    ConnectorNo auth
  • QuintaDB domain knowledge guide. Call this at the start of a session to learn field types, rel/linked_column rules, validation syntax, portal theme/color codes, and the correct workflow for building or modifying a project. Essential for external AI clients (Claude, ChatGPT) connecting via MCP.
    ConnectorNo auth
  • [EXPERIMENTAL] Read a file from the per-workspace sandbox filesystem (build artifacts, test output, logs). Requires Cloudflare Containers; degrades to 503 otherwise.
    ConnectorNo auth
  • QuintaDB domain knowledge guide. Call this at the start of a session to learn field types, rel/linked_column rules, validation syntax, portal theme/color codes, and the correct workflow for building or modifying a project. Essential for external AI clients (Claude, ChatGPT) connecting via MCP.
    ConnectorNo auth
  • QuintaDB domain knowledge guide. Call this at the start of a session to learn field types, rel/linked_column rules, validation syntax, portal theme/color codes, and the correct workflow for building or modifying a project. Essential for external AI clients (Claude, ChatGPT) connecting via MCP.
    ConnectorNo auth
  • OPENAI-COMPATIBLE chat completions, fast tier — point any OpenAI SDK at base_url https://api.webbersites.com/v1 and pay per call in USDC instead of holding provider API keys. Models: claude-haiku-4-5 (default), gemini-2.5-flash, gemini-2.5-flash-lite, gpt-5-mini, gpt-5-nano. Caps: 16,000 input chars, 1,024 output tokens, text-only, no streaming. One flat price per call; the x402 payment IS the auth. ($0.01 per call, paid via x402)
    ConnectorNo auth
  • Scan for live arbitrage: DEX price dislocations, flash-loan-fundable routes, cross-chain spreads, or prediction-market mispricings. [Paid: $0.60–$1.00 per call from your Einstein credit balance. Free alternatives exist for several of these — see list_einstein_capabilities.]
    ConnectorNo auth