Ateam MCP vs Blockrun MCP
A side-by-side look at the Ateam MCP and Blockrun MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Ateam MCP for aggregators work as a local process; choose Blockrun MCP for aggregators as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Ateam MCP when
- You need dedicated capabilities in the Aggregators domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
ADAS_TENANT, ADAS_API_KEY. - You want tools like
ateam_bootstrap, ateam_auth, ateam_get_spec.
Choose Blockrun MCP when
- You need dedicated capabilities in the Aggregators domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: other.
- You want tools like
blockrun_wallet, blockrun_chat, blockrun_models.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Aggregators | Aggregators |
| Quality signal | 64/100 · Good | 72/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | API key required | other |
| Pricing | BYOK (pay the provider) | Free |
| Required env vars | ADAS_TENANTADAS_API_KEY | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 1 | 391 |
| Directory activity | 3 views 0 installs 0 upvotes | 4 views 0 installs 0 upvotes |
| Tools | 59 | 19 |
| Full listing | View Ateam MCP | View Blockrun MCP |
Tools & capabilities
Ateam MCP tools 59
ateam_bootstrapREQUIRED onboarding entrypoint for A-Team MCP. MUST be called when user greets, says hi, asks what this is, asks for help, explores capabilities, or when MCP is first connected. Returns platform explanation, example solutions, and assistant behavior instructions. Do NOT improvise an introduction — call this tool instead.ateam_authAuthenticate with A-Team. Required before any tenant-aware operation (reading solutions, deploying, testing, etc.). The user can get their API key at https://mcp.ateam-ai.com/get-api-key. Only global endpoints (spec, examples, validate) work without auth. IMPORTANT: Even if environment variables (ADAS_API_KEY) are configured, you MUST call ateam_auth explicitly — env vars alone are not sufficient. For cross-tenant admin operations, use master_key instead of api_key.ateam_get_specGet the A-Team specification — schemas, validation rules, system tools, agent guides, and templates. Start here after bootstrap to understand how to build skills and solutions. Use 'section' to get just one part of the skill spec (much smaller than the full spec). Use 'search' to find specific fields or concepts across the spec. When designing a persona that orchestrates logic via run_python_script (the Python-as-orchestrator pattern), also fetch topic='python_helpers' — that returns the adas.* helper namespace reference. Skills designed without knowing about adas.* produce 5-10x larger / brittler scripts. When wiring widgets (UI plugins) into a solution, fetch topic='widgets' — that returns the widget spec (catalog model, how_to_use blocks, opener_call shape, persona phrasing rules, binding semantics) so you can declare `ui_plugins` correctly. For the live catalog of widgets actually available in a deployed tenant, use ateam_get_widget_catalog instead.ateam_get_workflowsGet the builder workflows — step-by-step state machines for building skills and solutions. Use this to guide users through the entire build process conversationally. Returns phases, what to ask, what to build, exit criteria, and tips for each stage.ateam_get_examplesGet complete working examples that pass validation. Study these before building your own.ateam_design_advisorCONSULT THIS DURING DESIGN — before and while you design a skill/solution. Describe what you're building; it returns POINTERS to the platform capabilities that fit (per-actor storage, widgets, triggers, sub-agents, mobile data, run-scripts, multi-skill, GitHub, …), each with the /spec topic to read next (via ateam_get_spec) and the tool to wire it. Also returns 'missing' hints (capabilities your goal implies but the design hasn't wired) and lifecycle hints (e.g. connect GitHub when the project will iterate). ADVISORY ONLY — you decide and own the design. Stateless: pass the current design_state each call; consult it as often as you like as the design evolves. If the reply carries `truncated: true`, the answer ran past the length budget and was CUT OFF: what is there is correct, but a capability's ABSENCE proves nothing — ask again with a narrower goal, or use ateam_spec_search, before concluding the platform lacks something.ateam_spec_searchSemantic search over the FULL ateam platform /spec documentation — the deep fallback behind ateam_design_advisor. Ask a natural-language 'how do I…' question and get the most relevant doc chunks (with their topic + heading), then read the full topic via ateam_get_spec(topic). Use this when the advisor's pointer isn't enough, or for details/examples on anything — including topics outside the curated capability list. Read-only.ateam_build_and_runDEPLOY THE CURRENT MAIN BRANCH TO A-TEAM CORE. ⚠️ HEAVIEST OPERATION (60-180s): validates solution+skills → deploys all connectors+skills to Core (regenerates MCP servers) → health-checks → optionally runs a warm test → auto-pushes to GitHub. 🌳 DEV/PROD WORKFLOW: 1. Edit files → ateam_github_patch (writes to `dev` branch by default) 2. (Optional) Preview what's about to ship → ateam_github_diff 3. Ship dev → main → ateam_github_promote (merges + auto-tags `prod-YYYY-MM-DD-NNN`) 4. Deploy main to Core → ateam_build_and_run This tool ALWAYS deploys the `main` branch — there is no `ref` parameter. To deploy in-progress dev work, first promote it. AUTO-DETECTS GitHub repo: if you omit mcp_store and a repo exists, connector code is pulled from main automatically. First deploy requires mcp_store. After that, edit via ateam_github_patch + promote, then build_and_run. For small changes prefer ateam_patch (faster, incremental). Requires authentication.ateam_test_skillSend a test message to a deployed skill and get the execution result. Wait modes (wait_for): • 'root' (default, back-compat) — wait until the message's root job completes, return single-job result. Fast, ignores any sub-skills the root delegated to via askAnySkill. • 'chain' — wait until EVERY job in the chain (root + handoffs + askAnySkill subcalls, recursively) reaches a terminal state, then return the full chain tree. Use when testing multi-skill flows (orchestrator → workers, builders → sub-builders, etc.). The response.chain field carries chainJobs[] with parentJobId/relation/depth and executionSteps[] with tool-nesting (opId/parentOpId/_toolDepth). Legacy: wait:false is equivalent to wait_for:'never' — returns job_id immediately for polling via ateam_test_status. wait:true is the same as the default wait_for:'root'.ateam_test_notificationFire a REAL notification at an existing actor in a deployed solution — for end-to-end testing of the system-initiated notification path (telegram/push/app channels). Unlike ateam_test_skill (synthetic test actor with no channels) and ateam_conversation (user-initiated thread), this calls the /api/internal/notify-user path that PCM and other sibling services use — so the actor's real enabled channels actually receive the message. Use for: • Channel fan-out smoke (does telegram/push/app actually receive it?) • Delivery-result verification (per-channel ok/failed in the response). Auth: forwards your authed api_key to Core (no master-secret involvement). Tenant is pinned by the key itself — cross-tenant targeting is structurally impossible. ⚠️ SAFETY: • The text is prefixed with [TEST] in the actual notification — visible to the user, anti-phishing. • Rate-limited: 10 calls/min per session. • Every call is audited (caller, tenant, actor, content hash) regardless of outcome. • actor_id is scoped to your tenant — cross-tenant targeting is rejected by Core's per-tenant Mongo isolation. • reply_handler is NOT supported via api-key auth (Core ignores it). Routing the user's next reply to an arbitrary skill is a privilege-escalation surface. For routing/engagement tests, use ateam_test_skill.ateam_conversationSend a chat message to a deployed solution. No skill_id needed — the system auto-routes to the right skill. ALWAYS ASYNC: returns a chain_id immediately — the assistant's reply is NOT in this response (a conversation can run for minutes across handoffs + subcalls, so a synchronous wait would hit the 100s edge timeout → 524). POLL BY CHAIN, NEVER BY JOB: an individual job can terminate while the chain is still running, so poll ateam_chain_status(chain_id) on a loop (~2s) and stop when chain_done === true (or pending_question is set — the assistant is waiting on the user). That is the cheap chip-quick poll (Core's whole-chain computeChainStatus — the same thing the standard chat uses). Use ateam_get_chain(chain_id) only ONCE at the end if you want the full tree / per-job detail — it's too heavy to loop on. Multi-turn: pass the actor_id from a previous response back in to continue the same thread (e.g. reply to a confirmation prompt). Each call starts a new chain; the same actor_id maintains conversation context.ateam_test_pipelineTest the decision pipeline (intent detection → planning) for a skill WITHOUT executing tools. Returns intent classification, first planned action, and timing. Use this to debug why a skill classifies intent incorrectly or plans the wrong action.- +47 more on the listing page
Blockrun MCP tools 19
blockrun_walletCall this tool to manage the BlockRun payment wallet and control agent spending budgets. Call this FIRST if any other blockrun_* tool returns a payment/balance error. Call this to check your current USDC balance before expensive operations. Call this to set spending limits before spawning child agents. If this server is running on a BlockRun API key (BLOCKRUN_API_KEY), there is no wallet and no chain: status reports the account, and setup/qr/deposit/chain do not apply. Credit is managed at https://user.blockrun.ai/dashboard/credits. In wallet mode the server holds TWO wallets — one on Solana, one on Base — but pays on ONE active chain at a time. status shows both addresses/balances and which is active. New installs default to Solana; an existing Base wallet keeps Base until you switch. To switch chain (no env vars, no file editing, no restart): 1. action:"chain" chain:"solana" → provisions + activates the Solana wallet 2. action:"setup" → address + funding QR for the active chain Switch back with action:"chain" chain:"base". Almost everything now settles on either chain; only blockrun_defi (DefiLlama) and blockrun_modal are Base-only, plus native Anthropic (claude-*) in blockrun_chat. Actions: - status (default): Both wallet addresses + USDC balances, active chain, session spending - deposit: Buy USDC with a card — mints a one-time Coinbase Onramp link and opens it in the browser (Base only; funds settle into your own wallet). Paid tools auto-open this on an out-of-funds failure; call it directly to fund up front. - setup: Get funding instructions + QR code for the ACTIVE chain (call this when balance is 0) - qr: Open QR code (active chain) in system viewer - chain + chain:"base"|"solana": Switch the active payment chain (omit chain: to just see the current one) Budget controls: - budget + budget_action:"set" + budget_amount:1.00 → Set global spend cap - budget + budget_action:"check" (the default) → Report the cap, spend and remaining - budget + budget_action:"clear" → Remove a cap set here If the operator started the server with BLOCKRUN_BUDGET_LIMIT, that value is a ceiling this tool can only lower: set above it is clamped, clear restores it, and agent_limit is clamped to it. Only a restart with a new env raises it. Multi-agent orchestration: - delegate + agent_id:"research" + agent_limit:2.00 → Allocate $2 to a child agent - revoke + agent_id:"research" → Remove a child agent's cap (its spend is kept; re-delegating the id carries it) - report → See per-agent spending breakdown Usage pattern for multi-agent systems: 1. blockrun_wallet action:"delegate" agent_id:"worker-1" agent_limit:1.00 2. Pass agent_id:"worker-1" to all blockrun_chat/search/etc calls for that agent 3. blockrun_wallet action:"report" to audit spending Do NOT call this for actual AI queries — use blockrun_chat for that.blockrun_chatGet a second opinion from another AI model, or use a specialized model for a specific task. Notable modes: - mode:"powerful" → Claude Opus 5, Claude Opus 4.8, GPT-5.6-sol, Claude Fable 5 (frontier, 1M context) - mode:"reasoning" → Claude Opus 5, GPT-5.6-sol, Kimi K3, Grok 4.3, deepseek-v4-pro - mode:"coding" → Claude Opus 5, GPT-5.3-codex, Kimi K3, Grok Build, GLM-5.2 - mode:"cheap" → deepseek-v4-pro, Qwen3.7 Flash, MiniMax M3, Tencent Hy3 - mode:"glm" → Zhipu GLM-5 / 5.2 / 5.1 / 5-Turbo (strong at coding) - mode:"free" → free models (no cost) Pick directly: model:"anthropic/claude-opus-5", model:"moonshot/kimi-k3", model:"openai/gpt-5.6-sol", model:"xai/grok-4.5", model:"nvidia/gpt-oss-120b" (free). Run blockrun_models to see all available models with pricing.blockrun_modelsList available AI models with pricing. Use to discover models and compare costs.blockrun_imageGenerate or edit images via BlockRun. Pays with USDC on the ACTIVE chain — Base or Solana (see blockrun_wallet) — no separate API keys needed. Actions: - generate (default): Create image from text prompt - edit: Transform an existing image using img2img Generation models (1024x1024 base price; larger sizes cost more on gpt-image-*): - openai/gpt-image-2 ($0.06–0.12) — flagship, reasoning-driven, multilingual on-image text + character consistency (default) - openai/gpt-image-1 ($0.02–0.04) — GPT native image generation - google/nano-banana ($0.05) — Gemini-family image model - google/nano-banana-2 ($0.09) — Gemini 3.1 Flash, pro-level quality at Flash speed (1024x1024 only) - google/nano-banana-pro ($0.10; $0.15 at 4096px) — up to 4K, strongest photorealism - xai/grok-imagine-image ($0.02) — stylized, fast - xai/grok-imagine-image-pro ($0.07) — higher quality Grok Imagine - zai/cogview-4 ($0.015) — cheapest, photorealistic detailed scenes - bytedance/seedream-5-pro ($0.045; $0.09 when both dimensions exceed 1024) — Seedream 5.0 Pro; cheap widescreen at 1280x720 / 2048x1024, large formats up to 2848x1600 Edit (img2img) models: openai/gpt-image-2 (default), openai/gpt-image-1, google/nano-banana, google/nano-banana-2, google/nano-banana-pro Multi-image edit: pass an array of 2–4 source images to "image" to fuse them in one render (openai/* up to 4, google/* up to 3) — e.g. a subject plus a sprite layout guide, or a reference plus a brand logo. Source images and masks accept a base64 data URI, an http(s) URL, or a local file path (auto-encoded). Inpaint mask (openai/gpt-image-* only) via "mask"; not combinable with multiple source images.blockrun_musicGenerate music tracks via BlockRun x402 (async, client-polled). Generates a full-length ~3 minute MP3 track. Takes 1-3 minutes to complete. The tool submits the job and, for slower tracks, polls until it is ready. On the Base wallet payment settles only when a finished track is returned — if the job fails you are not charged; if this client gives up while a paid request is still in flight the gateway may still settle, and the error text says so. On Solana and on the account rail the job is billed when the gateway ACCEPTS it, so a job that later fails or outlives the poll budget is still charged — the error text says so and names the job, which stays claimable for ~48h. Model: minimax/music-2.5+ ($0.1575/track, up to ~4 min) Returns a permanent BlockRun-hosted URL.blockrun_speechAI voice via BlockRun x402 — speak text aloud (ElevenLabs or ByteDance Seed Audio), generate sound effects, list voices. Actions: - speak (default): text-to-speech. E.g. "speak this with the sarah voice". Price = chars/1000 × rate (min $0.001), quoted before payment. - sound_effect: cinematic sound effects from a text prompt, up to 22s ($0.0525/clip) - voices: list available voices (free) Models (speak): elevenlabs/flash-v2.5 ($0.05/1k chars, ~75ms, default), elevenlabs/turbo-v2.5 ($0.05/1k), elevenlabs/multilingual-v2 ($0.10/1k, narration), elevenlabs/v3 ($0.10/1k, most expressive), bytedance/seed-audio-1.0 (~$0.003/sec of output, est. from input length; max 3k chars in / 120s out) — prompt-DIRECTED audio: describe the voice, emotion, and sound staging in the input text itself ("a tired detective mutters, rain in the background: ..."); the voice parameter is ignored. Voice aliases (ElevenLabs models only): sarah (default), george, laura, charlie, river, roger, callum, harry — or any raw ElevenLabs voice_id. Returns a hosted audio URL — download immediately if you need to keep the file.blockrun_videoGenerate short AI videos via BlockRun x402 on the active Base or Solana chain (async, client-polled). Turns a text prompt (and optional seed image) into a short MP4 clip. The tool submits the job, then polls until the video is ready (typical total wall-time 60-180s; 9 min Base / 15 min Solana hard cap). On the wallet rails payment settles only when upstream returns a finished video — if the job fails you are not charged; if this client gives up while a paid poll is still in flight the gateway may still settle, and the error text says so. On the account rail the job is billed when the gateway accepts it, so a job that fails or outlives the poll budget is still charged — the error names it. Models. Every rate below is what you are CHARGED (margin and transaction fee included), at the 720p baseline Seedance renders by default with synced audio: - azure/sora-2 (~$0.105/sec, 720p + synced audio, text- or image-to-video) — OpenAI Sora 2 via Azure AI Foundry. duration_seconds must be 4, 8, or 12 (4s default -> ~$0.42/clip). image_url takes a NON-HUMAN reference image (faces are rejected upstream by moderation — use Seedance + RealFace for real people); same price as text-to-video. No RealFace, no last_frame_url. Base only for now: the Solana gateway quotes it as Seedance 2.0 at $1.135 and the tool refuses that quote unsigned. - xai/grok-imagine-video ($0.05/sec at 480p default, $0.07/sec at 720p; 8s default -> $0.401/clip, 1-15s) — stylized, fast. 480p/720p only. - bytedance/seedance-1.5-pro (~$0.071/sec, 4-12s, 5s default -> ~$0.35/clip) — cheapest Seedance, token-priced upstream - bytedance/seedance-2.0-mini (~$0.080/sec, 4-15s, 5s default) — 2.0-generation quality at roughly half the 2.0-fast rate; 720p ceiling; supports RealFace and first/last-frame - bytedance/seedance-2.0-fast (~$0.165/sec, 4-15s, ~60-80s gen) — sweet-spot price/quality; supports BytePlus RealFace assets - bytedance/seedance-2.0 (~$0.227/sec, 4-15s, up to 4K) — highest quality, and the ONLY model that renders true 4K; supports RealFace, first/last-frame and reference media - bytedance/seedance-2.5 (~$0.315/sec, 4-30s, 5s default) — long-form: double 2.0's length ceiling, multilingual. NOT a strict upgrade — it caps at 720p and does NOT support RealFace or first/last-frame. Use 2.0 for 1080p/4K or real-person video. Image-to-video is NOT cheaper than text-to-video on Seedance — same per-second rate. Higher resolutions ARE more expensive (token-priced: 1080p ~2.25x, 4K ~9x the 720p rate); the 402 quote is authoritative and is what gets charged. RealFace: to generate video of a SPECIFIC real person, first enroll them with blockrun_realface (returns a ta_xxxx asset id), then pass real_face_asset_id here with seedance-2.0, seedance-2.0-fast, or seedance-2.0-mini. Mutually exclusive with image_url. Returns a permanent blockrun-hosted MP4 URL (the gateway mirrors the asset to GCS so URLs don't expire).blockrun_realfaceEnroll a real person's face as a BytePlus RealFace asset, then drive Seedance 2.0 video with it (blockrun_video real_face_asset_id). A RealFace asset (ta_xxxx) lets Seedance 2.0 / 2.0-fast / 2.0-mini generate video of a SPECIFIC real person — not a generic seed image. Only those three models: seedance-2.5 is numerically newer but does NOT accept ta_ assets, and seedance-1.5-pro never did. Enrollment is a multi-step flow because BytePlus requires a live phone liveness check (the real person nods + blinks on camera) before a face photo can be uploaded. Actions: - init: FREE. Create an asset group + a phone H5 link. The tool renders the link as a QR code and opens it; the real person scans it on their phone and completes the ~1 min liveness check. Pass group_id to refresh an expired link. - status: FREE. Poll a group until status:"active" (ready_to_finalize:true). The H5 link is valid ~120s — re-init if it expires. - enroll: PAID ($0.01). Settles on Solana or Base from a wallet, or against your BlockRun account key. After the group is active, upload a clear front-facing photo (image_url) of the SAME person. Returns the ta_xxxx asset id. - portrait: PAID ($0.01). Settles on Solana or Base from a wallet, or against your BlockRun account key. Virtual Portrait — enroll an AI-GENERATED character from an image URL directly, NO liveness needed (one step: name + image_url → ta_xxxx). For fictional/AI characters only; for a real person use the init→status→enroll liveness flow. - list: FREE, WALLET MODE ONLY (assets are indexed by wallet address). List the RealFace + Virtual Portrait assets enrolled by this wallet (their ta_xxxx ids + names) so you can pick one for blockrun_video. Typical flow: 1. blockrun_realface action:"init" name:"Alice" → scan QR on phone, do liveness 2. blockrun_realface action:"status" group_id:"legacy_rf_…" → repeat until ready_to_finalize:true 3. blockrun_realface action:"enroll" name:"Alice" group_id:"legacy_rf_…" image_url:"https://…/alice.jpg" → ta_xxxx 4. blockrun_video model:"bytedance/seedance-2.0" real_face_asset_id:"ta_xxxx" prompt:"…" Privacy: BlockRun does not store face/liveness data — only the asset id, name, and the photo URL you supply.blockrun_searchGrok Live Search — real-time web + news with AI-summarized results and citations. PRICED PER SOURCE and expensive by default: $0.025 × max_results, +5% gateway buffer — default max_results=10 settles ~$0.26 (max_results=50 → ~$1.31). Pass a smaller max_results to cap spend; for a plain fact, 3 sources (~$0.08) is usually enough. Common shape: - body: { query: "...", sources: ["web","news"], max_results: 10, from_date: "YYYY-MM-DD", to_date: "YYYY-MM-DD" } `sources` accepts any subset of ["web","news"] (default ["web"] — pass both for news coverage). There is no X/Twitter source (removed upstream 2026-07-05; asking for it is refused before payment). `max_results` is 1–50 (default 10) and drives the price — pass a smaller value if you want to cap spend. Full request shape + worked examples in the `search` skill (`skills/search/SKILL.md`).blockrun_exaNeural web search via Exa — understands meaning, not just keywords. Great for research. Common paths (all POST, body shapes documented in the exa-research skill): - search — body: { query, numResults?, category?, includeDomains?, excludeDomains? } ($0.010 base + tx fee) - answer — body: { query } ($0.010 base + tx fee) - contents — body: { urls: [...] } ($0.002/URL + ONE tx fee, up to 100) - find-similar — body: { url, numResults? } ($0.010 base + tx fee) Tx fee = the gateway's flat network fee, $0.001 today (we reserve $0.002); the 402 header carries the exact charge. Categories for search: "news", "research paper", "company", "tweet", "github", "pdf". Full request/response shapes + worked research workflows in the `exa-research` skill.blockrun_marketsPrediction market + derivatives data via Predexon aggregator. Flat $0.0075 base per call (every endpoint) plus the gateway's network fee — $0.001 on Base today, none quoted on Solana; the 402 header carries the exact charge (we reserve $0.0095). POLYMARKET (Tier 1): - polymarket/events, polymarket/markets — list events/markets (filter, sort, paginate) - polymarket/markets/keyset, polymarket/events/keyset — same data, cursor-based keyset pagination (params: { pagination_key }) - polymarket/crypto-updown — crypto up/down markets - polymarket/market-price/:token_id — current/historical price - polymarket/candlesticks/:condition_id — OHLCV by market - polymarket/candlesticks/token/:token_id — OHLCV by single outcome token - polymarket/volume-chart/:condition_id — volume w/ YES/NO split - polymarket/orderbooks, polymarket/trades, polymarket/activity - polymarket/markets/:token_id/volume, polymarket/markets/:condition_id/open_interest - polymarket/positions — user positions - polymarket/leaderboard, polymarket/leaderboard/market/:condition_id - polymarket/cohorts/stats, polymarket/market/:condition_id/top-holders - polymarket/uma/markets, polymarket/uma/market/:condition_id — UMA oracle questions/timeline POLYMARKET (Tier 2 — wallet/smart-money analytics): - polymarket/wallet/:wallet — full smart-wallet profile - polymarket/wallet/:wallet/markets, .../similar - polymarket/wallet/pnl/:wallet, .../positions/:wallet, .../volume-chart/:wallet - polymarket/wallets/profiles — batch profiles, GET with params: { addresses } (POST 404s); polymarket/wallets/filter — AND/OR filter - polymarket/market/:condition_id/smart-money, polymarket/markets/smart-activity WALLET IDENTITY & CLUSTERING (Tier 2) — cross-context labels + on-chain relationship graph: - polymarket/wallet/identity/:wallet — fetch identity + profile metadata for one wallet - polymarket/wallet/identities — POST { addresses: [...] } for bulk lookup (up to 200 wallets) - polymarket/wallet/:address/cluster — discover wallets connected via on-chain transfers + identity proofs SPORTS — sports/* (categories, markets, markets/:game_id, outcomes/:predexon_id) DEGRADED, do not call: Predexon 500 on every call since 2026-08-04; the gateway releases the payment on that upstream 500. Use markets/search { q: "NBA" } or polymarket/events { search: "NBA" } instead — no live route takes a "league" param. KALSHI: kalshi/markets, kalshi/trades, kalshi/orderbooks LIMITLESS / OPINION / PREDICT.FUN: {platform}/markets, {platform}/orderbooks BINANCE FUTURES: binance/candles/:symbol, binance/ticks/:symbol CROSS-PLATFORM: - markets/search — search every venue in one call (search term is "q"). The only canonical-layer route left: markets, markets/listings, outcomes/:id and matching-markets(/pairs) were removed upstream 2026-08-04 and 404 before payment. REQUEST CONTRACTS: - Discover current markets with markets/search (its search term is "q"), then resolve the chosen Polymarket market with polymarket/markets/keyset and condition_id. - On polymarket/markets{,/keyset} the free-text filter is "search" (NOT "q"), and status:"open"/"closed" replaces Gamma's active/closed. "sort", "end_after", and "end_before" are supported; "order"/"ascending" are not. - Candlesticks interval is integer minutes ("1440", not "1h"); it is OPTIONAL (the server defaults). Which intervals a market serves varies — 1440 may work where 60 does not. start_time/end_time are Unix seconds. - polymarket/orderbooks requires token_id plus start_time/end_time in Unix milliseconds. - Smart-money needs a smart-wallet CRITERION (min_trades, min_volume, min_roi, min_*_pnl, min_win_rate, min_profit_factor). "window" only scopes time and is NOT sufficient on its own. Default: { window: "30d", min_trades: "100" }. Pass query params via 'params' (GET) — a '?' in 'path' is refused before payment, because path-carried values bypass the pre-payment checks above. Use 'body' only for POST endpoints (e.g. polymarket/wallet/identities).blockrun_priceRealtime quotes and OHLC history for crypto, FX and commodities (Pyth-backed), plus the ticker catalog for 12 stock markets. - action="price" — realtime quote for a symbol - action="history" — OHLC bars between from/to (unix seconds) - action="list" — discovery: list available symbols (free) Pricing: - crypto / fx / commodity: FREE across price, history and list - stocks / usstock: list (ticker catalog) FREE; price/history NOT SERVED — gateway 501 before payment since 2026-09-05, nothing charged, do not retry Stocks markets: us, hk, jp, kr, gb, de, fr, nl, ie, lu, cn, ca (required when category="stocks"). Examples: - { action: "price", category: "crypto", symbol: "BTC-USD" } - { action: "price", category: "fx", symbol: "EUR-USD" } - { action: "history", category: "crypto", symbol: "ETH-USD", resolution: "D", from: 1700000000, to: 1710000000 } - { action: "list", category: "crypto", query: "sol" }- +7 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Ateam MCP
{
"mcpServers": {
"ariekogan-ateam-mcp": {
"command": "npx",
"args": [
"-y",
"@ateam-ai/mcp"
],
"env": {
"ADAS_TENANT": "YOUR_ADAS_TENANT_HERE",
"ADAS_API_KEY": "YOUR_ADAS_API_KEY_HERE"
}
}
}
}
Blockrun MCP
{
"mcpServers": {
"blockrunai-blockrun-mcp": {
"command": "npx",
"args": [
"-y",
"@blockrun/mcp@latest"
]
}
}
}
Frequently asked questions
Ateam MCP is categorized under Aggregators and uses a local stdio subprocess. Blockrun MCP belongs to Aggregators and uses a local stdio subprocess. Pick Ateam MCP for aggregators work and Blockrun MCP for aggregators.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Ateam MCP is bring-your-own-key: usage is billed by the API provider you supply a key for. Auth: api key required. Blockrun MCP is listed as free. Auth: other. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add ariekogan-ateam-mcp and blockrunai-blockrun-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Ateam MCP has a quality signal of 64/100 (Good) with 3 views, 0 installs and 1 GitHub stars. Blockrun MCP has 72/100 (Great) with 4 views, 0 installs and 391 GitHub stars.