SwarmIO
Server Details
AI that does real work for you: cited web research, plans, finance, horoscopes. Self-serve.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 14 tools
Most tools have clearly distinct purposes, aided by explicit cross-references (e.g. search vs web.search, market.pulse vs news.brief, runs.get vs runs.wait vs runs.report). The content-retrieval cluster (search, web.search, fetch, market.pulse, news.brief) is somewhat crowded, but the descriptions do draw the boundaries. A few names like fetch/search rely heavily on description text to disambiguate.
Strong dotted namespace.verb pattern across most tools (billing.balance, runs.launch, market.pulse, modes.list, news.brief, route.classify, web.search). Deviations are the bare verbs `search` and `fetch`, which break the otherwise consistent convention but remain readable.
14 tools is well within a healthy range and each earns its place: billing (2), run lifecycle (5), and content/discovery (5-6) plus routing helpers. No redundant filler; the set is scoped to the platform's actual workflows.
Run lifecycle is thoroughly covered (launch, get, wait, report, cancel), and billing and content access are both present. Minor gaps: there's no runs.list to enumerate a caller's run history, and no billing history/plan-change operation beyond balance and topup_terms.
Available Tools
14 toolsbilling.balanceBRead-onlyInspect
The caller's credit balance and plan state.
Inputs: no named parameters. Returns: plan, balance, user_id, currency, +2 more
billing.topup_termsARead-onlyInspect
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.
Inputs: no named parameters. Returns: how, asset, pay_to, enabled, +6 more
fetchARead-onlyInspect
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.
Inputs: id (required). Returns: id, url, text, title, +1 more
market.pulseARead-onlyInspect
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.
Inputs: no named parameters. Returns: free, news, next, as_of, +4 more
modes.listARead-onlyInspect
The launchable modes with a one-line contract for each. Static; never charged, no credentials needed.
Inputs: no named parameters. Returns: modes, route_first
news.briefARead-onlyInspect
PAID, 5¢ per call over x402 (USDC on Base, no account): today's market-news brief — this platform's newest published news digest synthesized with the live market wire into a cited bullet list, every finding ending with its source URL. No input required; the settle happens over HTTP, where the payment headers live: this tool returns the exact steps. The FREE raw material it is written from is market.pulse on this same server (the digest stories and wire headlines, un-synthesized).
Inputs: no named parameters. Returns: how, usd, free_raw_data
route.classifyARead-onlyInspect
Classify a freeform request into the right mode (research, news, finance, astrology, …) before spending a run. Never charged.
Inputs: prompt (required). Returns: mode, fields, from_llm, rationale, +2 more
runs.cancelADestructiveInspect
Stop a running job.
Inputs: run_id (required). Returns: run_id, status
runs.getARead-onlyInspect
A run's status and metadata. Poll until status is completed/failed/cancelled.
Inputs: run_id (required). Returns: meta, error, usage, status, +3 more
runs.launchAInspect
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).
Inputs: mode (required), input (required), max_workers. Returns: run_id, status, estimated_credits
runs.reportARead-onlyInspect
The finished, cited report for a completed run (report_text is markdown).
Inputs: run_id (required). Returns: report_text
runs.waitARead-onlyInspect
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.
Inputs: run_id (required), timeout_secs. Returns: run, report, run_id, status, +2 more
searchARead-onlyInspect
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.)
Inputs: query (required). Returns: results
web.searchARead-onlyInspect
FREE, no key, no account: LIVE web search, 25 queries a day per caller, up to 5 results each ({results:[{url,title,snippet,published}], quota, report}). This is the open web, not the published corpus — for the platform's finished reports use search. Over the daily quota the paid leg is $0.02 per call over x402 (USDC on Base): POST https://ioswarm.io/api/v1/search with the same JSON body and no payment header, read the 402, sign the EIP-3009 authorization, re-send with X-PAYMENT (v1) or PAYMENT-SIGNATURE (v2) — no account is created. The response's report field shows the one-call cited research brief (5¢, pay-only) for when raw results are not enough.
Inputs: query (required), k. Returns: quota, report, results
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Vedic and Western astrology for AI agents: charts, dasha, matchmaking, panchanga, numerology, tarot.
Daily horoscopes for AI agents: one playful forecast per zodiac sign, every day.
Real astrology for AI agents: cosmic weather, synastry, timing, astrocartography, and divination.
Western natal charts, horoscopes, transits and synastry for AI agents, verified vs NASA JPL.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables fully local, zero-cost autonomous research by planning questions, searching and reading web pages, generating cited summaries or reports, and retaining semantic memory across sessions.MIT
- AlicenseNot gradedqualityDmaintenanceWeb search, clean page reading & one-call research dossiers for AI agents. No API key — your agent does the synthesis.MIT
- AlicenseAqualityDmaintenanceResearches any company in ~10 seconds using 10 data sources. Returns structured reports with bull/bear verdict for stocks, crypto, and private companies.212AGPL 3.0

YesHelloofficial
AlicenseAqualityDmaintenanceDigital business cards, lead capture forms, and service listings - built and managed by AI. 63 tools with live browser editing, stock photos, web scraping, and guided tours.6MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.