此 MCP 可以做什么
Launches agentic web research runs for cited reports covering research, news, finance, products, trips, and related modes, with report search and retrieval.
功能
工具
12
工具
billing.balance
The caller's credit balance and plan state.
只读
输入模式
{'type': 'object', 'properties': {}}
输出模式
{'type': 'object', 'required': ['balance'], 'properties': {'plan': {'type': 'string'}, 'balance': {'type': 'number', 'description': 'Credits available right now.'}, 'user_id': {'type': 'string'}, 'currency': {'type': 'string'}, 'spent_total': {'type': 'number', 'description': 'Credits ever spent on runs.'}, 'granted_total': {'type': 'number', 'description': 'Credits ever granted (welcome + top-ups).'}}, 'additionalProperties': True}
billing.topup_terms
How to refill credits machine-to-machine: USDC on Base to a published address, verified on-chain. Returns the pay_to address, minimum, and rate. Public — no credentials needed.
只读
输入模式
{'type': 'object', 'properties': {}}
输出模式
{'type': 'object', 'required': ['enabled', 'network', 'asset', 'contract', 'min_usd', 'credits_per_usd', 'min_confirmations', 'how'], 'properties': {'how': {'type': 'string', 'description': 'The exact top-up procedure, step by step.'}, 'asset': {'type': 'string', 'description': "'USDC'."}, 'pay_to': {'type': 'string', 'description': 'The receiving address — present when enabled is true.'}, 'enabled': {'type': 'boolean', 'description': 'False while the operator has published no receiving address.'}, 'min_usd': {'type': 'number', 'description': 'Smallest top-up accepted, in USD.'}, 'network': {'type': 'string', 'description': "'base'."}, 'chain_id': {'type': 'integer', 'description': '8453 (Base mainnet).'}, 'contract': {'type': 'string', 'description': 'The USDC token contract to transfer.'}, 'credits_per_usd': {'type': 'number', 'description': 'Base rate; volume bonus applies on top.'}, 'min_confirmations': {'type': 'integer', 'description': 'Confirmations required before crediting.'}}, 'additionalProperties': True}
fetch
Read one report by the id search returned: the full markdown text with its citations and evidence header, plus title, url and metadata. Public reports need no key; a caller's own reports need theirs.
只读
输入模式
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'description': 'A result id from search (a run id).'}}}
输出模式
{'type': 'object', 'required': ['id', 'title', 'text', 'url'], 'properties': {'id': {'type': 'string'}, 'url': {'type': 'string'}, 'text': {'type': 'string', 'description': 'The report as markdown.'}, 'title': {'type': 'string'}, 'metadata': {'type': 'object', 'additionalProperties': True}}, 'additionalProperties': True}
market.pulse
FREE, no key, no account: live prices for BTC, ETH, SOL, AMZN and NVDA with the session's change, plus today's news — the platform's newest published news digest parsed into stories with source links, and the market wire's latest headlines. Refreshed every minute (prices) and every ten minutes (news). Call this first to see what the swarm's data looks like before spending anything.
只读
输入模式
{'type': 'object', 'properties': {}}
输出模式
{'type': 'object', 'required': ['as_of', 'prices', 'news'], 'properties': {'free': {'type': 'boolean', 'description': 'Always true — this call is never charged.'}, 'news': {'type': 'object', 'properties': {'as_of': {'type': ['string', 'null']}, 'digest': {'type': ['object', 'null'], 'description': 'The newest published news digest, parsed: {title, as_of, report_url, stories:[{headline, link, source, excerpt}]}. Null when no digest ran in the last 36 hours.'}, 'headlines': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'description': 'Latest market-wire headlines: {headline, link, publisher, published, summary}.'}}, 'additionalProperties': True}, 'next': {'type': 'object', 'description': 'How to get the same data over MCP and how to commission a real report.', 'additionalProperties': True}, 'as_of': {'type': 'string', 'description': 'RFC 3339 time this document was rendered.'}, 'prices': {'type': 'array', 'items': {'type': 'object', 'required': ['symbol', 'price', 'currency', 'source', 'as_of'], 'properties': {'as_of': {'type': 'string'}, 'price': {'type': 'number'}, 'source': {'type': 'string', 'description': 'pyth | yahoo.'}, 'symbol': {'type': 'string'}, 'currency': {'type': 'string'}, 'change_pct': {'type': ['number', 'null'], 'description': 'Session change in percent; null where the source has no session (crypto spot).'}}, 'additionalProperties': True}, 'description': 'One entry per symbol that priced this cycle, in list order.'}, 'symbols': {'type': 'array', 'items': {'type': 'string'}, 'description': 'The fixed symbol list served.'}, 'attribution': {'type': 'string'}, 'prices_as_of': {'type': ['string', 'null']}}, 'additionalProperties': True}
modes.list
The launchable modes with a one-line contract for each. Static; never charged, no credentials needed.
只读
输入模式
{'type': 'object', 'properties': {}}
输出模式
{'type': 'object', 'required': ['modes'], 'properties': {'modes': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'contract'], 'properties': {'id': {'type': 'string', 'description': 'Pass to runs.launch as mode.'}, 'contract': {'type': 'string', 'description': 'What the mode does, one line.'}}, 'additionalProperties': True}}, 'route_first': {'type': 'string', 'description': 'How to classify a freeform prompt into a mode id.'}}, 'additionalProperties': True}
route.classify
Classify a freeform request into the right mode (research, news, finance, astrology, …) before spending a run. Never charged.
只读
输入模式
{'type': 'object', 'required': ['prompt'], 'properties': {'prompt': {'type': 'string', 'description': "The freeform request to classify, e.g. 'compare the best espresso grinders under $300'."}}}
输出模式
{'type': 'object', 'required': ['mode', 'confidence'], 'properties': {'mode': {'type': 'string', 'description': 'The chosen mode id — pass it to runs.launch.'}, 'fields': {'type': 'object', 'description': 'Fields the router extracted from the prompt (mode-specific).'}, 'from_llm': {'type': 'boolean', 'description': 'True when the LLM router answered, false for the offline heuristic.'}, 'rationale': {'type': 'string', 'description': 'Why this mode was picked.'}, 'alternates': {'type': 'array', 'description': 'Other plausible modes, best first.'}, 'confidence': {'type': 'number', 'description': 'Router confidence, 0–1.'}}, 'additionalProperties': True}
runs.cancel
Stop a running job.
可能执行破坏性操作
输入模式
{'type': 'object', 'required': ['run_id'], 'properties': {'run_id': {'type': 'string', 'description': 'The run_id returned by runs.launch.'}}}
输出模式
{'type': 'object', 'required': ['run_id', 'status'], 'properties': {'run_id': {'type': 'string'}, 'status': {'type': 'string', 'description': "'cancelling' — the run unwinds itself; poll runs.get for the terminal state."}}, 'additionalProperties': True}
runs.get
A run's status and metadata. Poll until status is completed/failed/cancelled.
只读
输入模式
{'type': 'object', 'required': ['run_id'], 'properties': {'run_id': {'type': 'string', 'description': 'The run_id returned by runs.launch.'}}}
输出模式
{'type': 'object', 'properties': {'meta': {'type': 'object', 'description': 'Run metadata: id, mode, title, timing.'}, 'error': {'type': ['string', 'object', 'null'], 'description': 'Failure detail when status is failed, else null.'}, 'usage': {'type': ['object', 'null'], 'description': 'Token meters for the run — null while the run is still running, an object once it settles.'}, 'status': {'type': 'string', 'description': 'running | completed | failed | cancelled.'}, 'cancelling': {'type': 'boolean', 'description': 'A stop was requested but the run has not unwound yet.'}, 'has_report': {'type': 'boolean', 'description': 'True once runs.report will answer with the report.'}, 'finished_at': {'type': ['string', 'null'], 'description': 'RFC 3339 completion time; null while running.'}}, 'additionalProperties': True}
runs.launch
Launch a run: agents search the web, read sources, and write a cited report — real work, done for the caller. BILLED from the caller's credits. Returns the run record; poll runs.get until completed, then runs.report. Modes: research, news, product, trips, trainer, finance, astrology, horoscope (astrology/horoscope take Birth date constraint lines — see https://ioswarm.io/llms.txt).
可访问外部资源
输入模式
{'type': 'object', 'required': ['mode', 'input'], 'properties': {'mode': {'type': 'string', 'description': "A mode id from modes.list, e.g. 'research'."}, 'input': {'type': 'string', 'description': "The question or brief. astrology/horoscope take constraint lines ('- Birth date: YYYY-MM-DD', optional Birth time + Timezone, Latitude/Longitude) — contract at https://ioswarm.io/llms.txt."}, 'max_workers': {'type': 'integer', 'description': 'Optional parallelism override (worker count). Omit for the mode default.'}}}
输出模式
{'type': 'object', 'required': ['run_id', 'status'], 'properties': {'run_id': {'type': 'string', 'description': "The run's id — pass to runs.get / runs.report / runs.cancel."}, 'status': {'type': 'string', 'description': "'running' on acceptance."}, 'estimated_credits': {'type': 'number', 'description': 'The credit estimate reserved at launch; settled from real usage at completion.'}}, 'additionalProperties': True}
runs.report
The finished, cited report for a completed run (report_text is markdown).
只读
输入模式
{'type': 'object', 'required': ['run_id'], 'properties': {'run_id': {'type': 'string', 'description': 'The run_id returned by runs.launch.'}}}
输出模式
{'type': 'object', 'properties': {'report_text': {'type': 'string', 'description': 'The full report as markdown, citations inline.'}}, 'additionalProperties': True}
runs.wait
Block until a run finishes, then return its record — and its report when it completed. Runs take 3–10 minutes; call this instead of polling runs.get in a loop. Returns early with timed_out=true after timeout_secs (default 90, max 240): call it again with the same run_id to keep waiting. Never charged.
只读
输入模式
{'type': 'object', 'required': ['run_id'], 'properties': {'run_id': {'type': 'string', 'description': 'The run_id returned by runs.launch.'}, 'timeout_secs': {'type': 'integer', 'description': 'How long this call may wait before returning the current status. Default 90, max 240.'}}}
输出模式
{'type': 'object', 'required': ['run_id', 'status', 'timed_out'], 'properties': {'run': {'type': 'object', 'description': 'The run record (as runs.get).'}, 'report': {'type': ['object', 'null'], 'description': 'The report (as runs.report) when status is completed, else null.'}, 'run_id': {'type': 'string'}, 'status': {'type': 'string', 'description': 'running | completed | failed | cancelled.'}, 'timed_out': {'type': 'boolean', 'description': 'True when the wait window elapsed first — call again.'}, 'waited_secs': {'type': 'integer'}}, 'additionalProperties': True}
search
Search the swarm's published research: the featured shelf, the operator's daily news / markets / AI digests, and — when a key is presented — the caller's own reports. Every hit is a finished, cited, evidence-graded report. Returns {results:[{id,title,url}]}; pass an id to fetch. No key needed for the public corpus. (The research-connector contract: this is what a ChatGPT or Claude connector calls.)
只读
输入模式
{'type': 'object', 'required': ['query'], 'properties': {'query': {'type': 'string', 'description': 'Words to match against report titles and text.'}}}
输出模式
{'type': 'object', 'required': ['results'], 'properties': {'results': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'title', 'url'], 'properties': {'id': {'type': 'string', 'description': 'Pass to fetch.'}, 'url': {'type': 'string', 'description': 'The public report page, or the API report URL for a private run.'}, 'kind': {'type': 'string', 'description': 'featured | free | own.'}, 'mode': {'type': 'string'}, 'title': {'type': 'string'}, 'finished_at': {'type': ['string', 'null']}}, 'additionalProperties': True}}}, 'additionalProperties': True}
历史
近期工具变更
已添加
modes.list
2026年9月17日 12:53
已添加
billing.topup_terms
2026年9月17日 12:53
已添加
billing.balance
2026年9月17日 12:53
已添加
runs.cancel
2026年9月17日 12:53
已添加
runs.report
2026年9月17日 12:53
已添加
runs.wait
2026年9月17日 12:53
已添加
runs.get
2026年9月17日 12:53
已添加
runs.launch
2026年9月17日 12:53
已添加
route.classify
2026年9月17日 12:53
已添加
fetch
2026年9月17日 12:53
已添加
search
2026年9月17日 12:53
已添加
market.pulse
2026年9月17日 12:53
发现
类似的 MCP 服务器
AI 代理人任務中樞
com.penguindriver/hub
Aggregates Taiwan-focused tools for AI service comparisons, cryptocurrency data, game information, health guidance, and other con…
The Stall
ai.intuitek.the-stall/the-stall
Provides pay-per-call tools for YouTube keyword research and research on stocks, crypto, DeFi, options, and macroeconomic data.
Valuein — SEC EDGAR Fundamentals & Smart-Money Data
io.github.valuein/mcp-sec-edgar
Provides point-in-time SEC EDGAR fundamentals, filings, ownership signals, financial analysis, valuation models, research reports…
Good Turn Studio (all tools)
io.github.GoodTurnStudio/all
Offers consumer utilities for insurance claim appeals, subscription cancellation, flight fare research, financial recovery resour…
equibles
io.github.daniel3303/equibles
Provides equity and market research tools covering SEC filings, company financials, portfolios, prices, options, macroeconomic da…
tollbooth
io.github.huwhitememes/tollbooth
Provides paid OSINT, web intelligence, security threat and vulnerability lookups, prediction-market analysis, financial data, leg…
EventTrader Research (read-only)
com.cymetica/event-trader-research
Offers read-only research on funds, event markets, order books, arena markets, crypto pools, backtests, and related financial ana…
World Monitor
app.worldmonitor/mcp
Delivers live geopolitical, conflict, country-risk, market, energy, climate, aviation, supply-chain, and macroeconomic intelligen…