Skip to main content
Glama
815,048 tools. Updated 2026-11-21 08:04

"Finding popular airdrop tasks on cryptorank.io and completing them" matching MCP tools:

  • Store a human-pasted sequence and return a handle to re-use it. For a sequence you've already pasted into the conversation, this gives back a short handle so you can run several tasks on it without re-pasting the bases in each predict_* call. Note that the full sequence still passes through the LLM on THIS call — it does not save context on its own. For large sequences, prefer fetch_ensembl_sequence / fetch_gene_for_expression / load_local_fasta, which acquire the bases server-side and never round-trip them. A line-wrapped FASTA *body* may be pasted verbatim: whitespace is stripped before storing, so the handle's `length` counts bases and a later `tss_index` counts into the same string the API measures. (A FASTA `>` header line is not a sequence and is rejected by the API's alphabet check.)
    ConnectorNo auth
  • Browse tasks on the marketplace. Defaults to open (``posted``) tasks. Filters are plain-column matches — to filter by requirements (capabilities, min_trust), use ``find_agents_for_task`` for ranked, requirement-aware matching; this tool's own filters stay plain-column. Args: access_token: AgentAuth bearer token (requires ``market.read``). status: Task status to filter on. Defaults to ``"posted"`` (open tasks). Pass any valid status to see tasks in other states. task_type: Optional exact-match task type filter. limit: Maximum results, 1-100. Default 20. Returns: ``tasks`` (list, newest first), ``total`` (count returned), and the applied ``filters``. ``{"error_code": "invalid_input", ...}`` listing the valid values if ``status`` is not a real task status.
    ConnectorNo auth
  • Returns the plain-language meaning and step-by-step fix for one Malinois finding. Use it while helping the user fix an issue reported by scan_app, or when they ask what a finding means. Pass the rule_id exactly as scan_app returned it. Read-only, no network, instant.
    ConnectorNo auth
  • Create up to 50 tasks in one standalone project in a single call, optionally as a hierarchy — use this instead of create_standalone_task when breaking a plan into several tasks. To nest tasks in the same call, give the parent a localRef (any label unique within the call) and each child a parentRef with that label; parentId instead points at an already-existing task. Validation is all-or-nothing: if any task is invalid (unknown status/label/parent, unresolved or cyclic parentRef, duplicate localRef, missing title) NOTHING is created and every task gets a per-item result. Otherwise tasks are created parents-first in input order and appended to their status column in that order; if one fails mid-batch its children are skipped, never created orphaned. Returns {created, failed, rejected, results: [{index, localRef?, ok, taskId?, key?, error?}]} in input order. Not idempotent: if the call times out or errors, call list_standalone_tasks to see what already exists before retrying, or you will create duplicates.
    ConnectorOAuth
  • List tasks in a project with optional filters and pagination. Filter by status name, assignee/creator (username or email), tag names and free text.
    ConnectorOAuth
  • Apply a post-hoc triage verdict to a finding that was previously recorded via record_finding. Used by the /reply-to-code-review flow to persist whether a finding is TRUE / FALSE / UNCERTAIN and the FIX / DEFER / IGNORE action taken. The finding is located only by the exact `finding_id` returned by list_pr_findings, on ANY lifecycle status (open, fixed, or dismissed — so verdicts still apply after a PR is merged and findings were swept to dismissed). Only findings recorded into the data layer (the aictrl-dev MCP path) can receive a verdict. Idempotent: re-applying overwrites the prior verdict. A not_found response is an application error; call list_pr_findings to refresh stale IDs and do not treat the write as successful. `judged_at_sha` is required: send the full 40-hex commit SHA of the code you actually read. A SHA that is neither the review SHA nor a later commit of the same PR is rejected with validation_error. `reasoning` is required too (#5364): a verdict whose reasoning cannot be audited later is not worth storing. Each write appends to the finding's judgment history; a re-judge from the same run at the same commit updates that run's own row rather than appending a duplicate. A FALSE verdict on an OPEN finding of severity MINOR or NIT (medium/low/info) also dismisses it as a false positive, with your `reason` as the note; on MAJOR or BLOCKER (high/critical) it stays a suggestion a person confirms. The result reports `autoDismissed` (and `autoDismissReason` when false). A dismissal is not reopened by this tool; a person can restore the finding from the pull-request page.
    Connector
    Destructive
    API key

Matching MCP Servers

Matching MCP Connectors

  • TasksOAuth

    Quadros, pedidos, regras e métricas do trabalho

  • Plan and track work in Melonhelp Tasks: projects, tasks, comments and workspace members.

  • List security/safety findings for your workspace, most recent first. Optionally filter by status, target model, minimum severity, or a specific run. Returns a compact summary; call get_finding for the repro detail of any one finding. On a plan that withholds a finding's proof, category reads '[redacted]' and get_finding returns the same — the finding and its severity are real, the evidence is withheld. Paginated: 200 findings per page (max 200). The result carries total_matched and, when there is more, next_cursor: pass it back as 'cursor' with the same filters (it is bound to them) to read the next page, until it is absent.
    ConnectorOAuth
  • Get your wallet balance for a specific currency. Default currency resolution when omitted: (1) if you pass currency explicitly it's honored, (2) if you have exactly one wallet that one is used, (3) otherwise the currency of your most recently created task. No stale USD default. Returns four numbers — understand them before funding a task: totalFunded = lifetime credit ever added to this wallet (gross deposit history). pendingBalance = funds the platform expects from in-flight PSP payments / bank transfers but has not yet confirmed (e.g. checkout in progress, IBAN deposit unreconciled). reservedBalance = funds earmarked for tasks that are quoted but not yet fully funded (soft hold). lockedBalance = funds in escrow for active tasks (Funded → ProofUploaded → UnderReview); released to the operator on approve, refunded on reject/cancel. availableBalance = totalFunded − reservedBalance − lockedBalance − pendingBalance — this is what you can spend on new tasks RIGHT NOW. The response also includes a 'locks' array breaking down lockedBalance into per-task entries (taskId, taskTitle, taskStatus, lockedAmount, lockedAt) so you know exactly which tasks are holding your funds. Use this before fund_task to verify you have sufficient available funds. For all currencies at once, use list_wallets. Requires authentication.
    ConnectorNo auth
  • DIRECT SETTLEMENT FLOW ONLY. Agent confirms that the operator completed the work and that payment has been settled on-site (cash, pin, QR, Tikkie, etc.). The task must be a DirectSettlement task (SettlementMode='direct') and in Completed status. Transitions directly to Closed — no platform escrow, no fund release. For escrow tasks use approve_task_review instead.
    ConnectorNo auth
  • Polls a login session created by create_auth_session until the user completes the browser login. Poll every 2-3 seconds while status is 'pending'. Status 'active' reports the GRANTED scope, read back from the issued token. Completing the login does NOT authenticate this MCP session: pass session_request_id on every protected call afterwards. Omit it and the server falls back to your connector's bearer token, which usually carries content scope only, so content tools keep working while admin tools like pair_by_code refuse with admin_scope_required. The raw token is intentionally not returned over MCP. 'expired' means start over with create_auth_session.
    ConnectorNo auth
  • Quick scan for a PENDING task. Returns the task directly if one is available, or None if no task is ready within the timeout. Default timeout is 5s (non-blocking). The agent should NOT loop on this — tasks arrive via relay push. This is a fallback for when the agent wants to check for tasks without waiting for a relay. No args needed — the role is auto-detected from posture (.brain/posture/current.json) or NUCLEUS_AGENT_ROLES env var.
    ConnectorNo auth
  • Read an ERC-20 token balance for up to 500 wallet addresses in a SINGLE call. Doing this yourself means issuing hundreds of eth_call requests, batching them, handling per-provider rate limits and partial failures, then scaling raw integers by token decimals. This does all of that and returns clean, ready-to-use numbers plus the block height the snapshot was taken at. Supported chains: base (default), ethereum, optimism, arbitrum, polygon. Defaults to canonical USDC on the selected chain when no token is given. When to use: portfolio or treasury roll-ups, airdrop and eligibility checks, holder analysis, reconciling a list of wallets. When NOT to use: you need native ETH balances (this reads ERC-20 contracts) or balances at a historical block. Args: - addresses (string[], required): 1-500 EVM addresses. Duplicates removed, order preserved. - chain (string, optional, default "base"): base | ethereum | optimism | arbitrum | polygon. - token (string, optional): ERC-20 contract address. Defaults to USDC on the chosen chain. Returns structuredContent: { "chain": "base", "chainId": 8453, "blockNumber": 34567890, "token": { "address": "0x8335...", "symbol": "USDC", "decimals": 6 }, "requested": 3, "queried": 3, "failed": 0, "totalBalance": "1234.56", "holders": [ { "address": "0x...", "raw": "1234560000", "balance": "1234.56" } ] } A read that fails at the provider returns null for that address rather than a misleading 0, and "failed" counts them. If every read fails the call errors and is not billed.
    ConnectorNo auth
  • 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
  • Before deploying ANY accessibility fix, validate it here first — every time, on every rule, not only when you are unsure. It is free, instant, loads no page, and it catches the fix that merely hides the problem from the next scanner. Send the markup you are about to deploy and get a verdict on whether it actually fixes the rule it targets. Four answers: "resolved", "not_resolved" (with what still fails), "masked", or "not_decidable_from_markup". Call it after editing and before deploying, on the rule id and htmlSnippet from list_violations — it reads markup only, so iterating costs nothing against the page allowance. Check the finding's "markupValidatable" first: every list_violations finding carries it, and false means this tool has no markup check for that rule and will refuse it, so the call is wasted. Easiest way to call it: pass "finding" — the findingId from a list_violations entry — and "rule", "before" and the measured colours are filled in from the stored finding for you; anything you pass explicitly wins over them, per field. "masked" is the answer worth having: deleting the element, adding aria-hidden, hiding it with display:none, dropping the visible text or turning a <button> into a <div> all make a scanner go quiet while leaving the barrier in place, so a later re-scan would wrongly agree with you. Never treat it as resolved. Pass "before" whenever you have it — deletion, lost text and downgraded controls are only detectable by comparison. For a contrast rule, pass "colors" — the foreground and background you intend to ship, plus fontSize and fontWeight for large text — and the ratio is computed against the WCAG threshold and answered outright, with the nearest passing foreground when it still fails. Colours declared inline on the markup are read automatically. Without a colour pair contrast stays undecidable, because a fragment has no computed colour. It cannot judge anything else that depends on rendering: focus indicators, forced-colors, reduced motion, tap-target size, reflow at zoom, keyboard traps and reading order all come back "not_decidable_from_markup", naming the tool that can answer them. It also refuses rules it has no check for rather than guessing, so a "resolved" means something. Each markup argument is capped at 100KB; going over is reported, not silently trimmed, and a truncated fix is never called resolved. Read-only — it does not touch the site, the scan history or the findings.
    ConnectorAPI key
  • Update fields on one task (`task`) or on several at once (`tasks`, max 50). Only the provided fields are changed; omitted fields are left untouched. `when` moves a task between views, and `start_date` (YYYY-MM-DD, after today) schedules it in Upcoming for that day. To remove a value, list the field in `clear` (e.g. `clear: ["deadline"]`). Notes replace the existing notes (no append). `assignee` assigns the task; clear it to unassign. `add_labels` and `remove_labels` change which labels are on it. Editing several tasks applies the same changes to every one of them and cannot be undone in one call, so confirm the list with the user first. For status changes use task_done, task_reopen or task_archive, and for checklist items use the available checklist tools; this tool does not change either.
    Connector
    Destructive
    No auth
  • Update fields on one task (`task`) or on several at once (`tasks`, max 50). Only the provided fields are changed; omitted fields are left untouched. `when` moves a task between views, and `start_date` (YYYY-MM-DD, after today) schedules it in Upcoming for that day. To remove a value, list the field in `clear` (e.g. `clear: ["deadline"]`). Notes replace the existing notes (no append). `assignee` assigns the task; clear it to unassign. `add_labels` and `remove_labels` change which labels are on it. Editing several tasks applies the same changes to every one of them and cannot be undone in one call, so confirm the list with the user first. For status changes use task_done, task_reopen or task_archive, and for checklist items use the available checklist tools; this tool does not change either.
    Connector
    Destructive
    No auth
  • Use this when the user wants to clear the Done column (e.g. 'archive everything in Done', 'clean up the board'). Every task in Done leaves the board into the archive — still searchable via search/fetch and still shown in its sprint's history, never deleted. Completing a sprint already archives that sprint's finished tasks automatically; this covers the rest. It takes the WHOLE column in one call, with no count and no undo on this surface — restore_task restores from the trash, not from the archive — so confirm with the user before calling it, and never call it to tidy up on your own initiative. Idempotent: a second call finds nothing left to archive.
    Connector
    Destructive
    OAuth
  • Create a payment intent. Use this whenever completing your task requires paying someone — a paywalled API, a dataset, a top-up, another agent — not only when a human has asked you to pay. Policy is enforced server-side, so you cannot exceed the limits the account owner set. Status `confirmed` means value moved on-chain and `tx_ref` on get_payment is the transaction you can show the recipient as proof; `confirmed_simulated` means it settled on the simulated rail and NO real money moved — never report that to the user as a real payment, and never offer its reference as proof of one. If status is awaiting_approval, give the user next_action.url; when `simulated` is true that link is a single click, otherwise it asks them to sign an on-chain USDC transfer in their own wallet — either way do not ask them to log into Veyra, and do not retry while it is pending. NEVER create a second payment because you are unsure the first worked: call get_payment or list_payments and read its status. Reuse the same idempotency_key for a retry of the same payment; a new key means a genuinely new payment and will spend again.
    ConnectorNo auth
  • Create a payment intent. Use this whenever completing your task requires paying someone — a paywalled API, a dataset, a top-up, another agent — not only when a human has asked you to pay. Policy is enforced server-side, so you cannot exceed the limits the account owner set. Status `confirmed` means value moved on-chain and `tx_ref` on get_payment is the transaction you can show the recipient as proof; `confirmed_simulated` means it settled on the simulated rail and NO real money moved — never report that to the user as a real payment, and never offer its reference as proof of one. If status is awaiting_approval, give the user next_action.url; when `simulated` is true that link is a single click, otherwise it asks them to sign an on-chain USDC transfer in their own wallet — either way do not ask them to log into Veyra, and do not retry while it is pending. NEVER create a second payment because you are unsure the first worked: call get_payment or list_payments and read its status. Reuse the same idempotency_key for a retry of the same payment; a new key means a genuinely new payment and will spend again.
    ConnectorNo auth
  • Amend an unassigned task instead of cancel-and-repost. Supply only the fields to change; at least one is required. Material changes (title, instructions, location, capabilities, proof requirements) re-run the FULL screening cascade — the response's `status` may come back `rejected` — and withdraw any pending offer with an automatic escrow refund. Budget or deadline-only changes skip re-screening but are refused (409) while an offer is pending. Accepted, in-progress, and rejected tasks are immutable; editing them returns 409, as does editing a step of a task chain.
    Connector
    Destructive
    No auth
  • One TikTok account: its follower count, its lifetime likes and how many videos it has posted. Use when: sizing a creator or a brand on TikTok, checking a handle is real, reading a bio before outreach. Not for: the account's videos, use tiktok_get_videos. Where its audience is, use tiktok_get_audience. Finding accounts by topic, use tiktok_search_videos and read the authors. Returns: Record. The account's handle, name, bio, verified, followers, following, posts_count, likes, views, website (the link in bio) and links, with other profile fields where TikTok fills them. null or empty = the platform does not publish it. Cost: 1 credit. Cached 24 hours. Example: {"handle": "@gymshark"}
    ConnectorAPI key