SqueezeOS — Institutional AI Market Intelligence MCP Server
answering
SqueezeOS — Institutional AI Market Intelligence is answering right now. Last checked 6 min ago. It exposes 15 tools.
Institutional AI market intelligence: squeeze scanner, options flow, council verdicts. x402 RLUSD.
The linked repository no longer exists on GitHub — it was deleted or made private.
Uptime history
47 days of history · worst day 48%
47 days agonow
96.7%
Uptime 24h
89 of 92 checks
15
Tools
read from the server
310 ms
Response time
average over 24h
open, no key
Access
streamable-http
What changed 156
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 20 August 2026. No other catalogue keeps this.
18 Sep
4 tools appeared
aftersearch_accept, aftersearch_quote, aftersearch_resolve and 1 more
1 Sep
a tool appeared
agent_web_access
31 Aug
74 tools disappeared
agentbids_discover, agent_economy, agent_routes_discover and 71 more
31 Aug
7 tools appeared
call_capability, capability_manifest, discover_capabilities and 4 more
31 Aug
4 tool descriptions were rewritten
call_capability, compare_capabilities, inspect_capability and 1 more
31 Aug
4 tools changed the parameters they ask for
call_capability, compare_capabilities, inspect_capability and 1 more
31 Aug
a tool changed version
27 Aug
3 tools appeared
agentbids_discover, bazaar_negotiator_discover, robinhood_rwa_intelligence
26 Aug
2 tools appeared
agent_routes_discover, knowledge_fabric_query
23 Aug
18 tool descriptions were rewritten
agent_economy, ccs_validate, council_verdict and 15 more
and 38 more, back to 20 August 2026
SqueezeOS — Institutional AI Market Intelligence does not always answer
Over the last week it answered 98.6% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.
run in your terminal
claude mcp add squeezeos --transport http https://squeezeos-api.onrender.com/mcp~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"squeezeos": {
"url": "https://squeezeos-api.onrender.com/mcp"
}
}
}~/.codex/config.toml
[mcp_servers.squeezeos]
url = "https://squeezeos-api.onrender.com/mcp".cursor/mcp.json
{
"mcpServers": {
"squeezeos": {
"url": "https://squeezeos-api.onrender.com/mcp"
}
}
}.vscode/mcp.json
{
"mcpServers": {
"squeezeos": {
"url": "https://squeezeos-api.onrender.com/mcp"
}
}
}Available tools 15
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
aftersearch
aftersearch_accept
Retry one immutable job with caller-supplied x402 authorization. payment_response is forwarded as PAYMENT-SIGNATURE; SML never signs or spends.
aftersearch_quote
Return fresh x402 PAYMENT-REQUIRED terms for one immutable job. A 402 is not payment.
aftersearch_resolve
Compile a query into intent, bounded Evidence Pack, immutable job and fresh-quote pointer; never spends.
aftersearch_verify_serp
Verify pasted SERP/AI text or one caller-provided public URL; returns confirm, contradict or missing with sources.
x402
x402_contract
Return the canonical SqueezeOS x402 v2 discovery contract. Exact spend terms remain authoritative only in the target resource's fresh PAYMENT-REQUIRED challenge.
x402_evidence
Read real settlement evidence recorded by the canonical x402 rail. A challenge or signature alone is never treated as revenue or settlement proof.
x402_readiness
Read the live canonical payment-rail readiness surface before attempting a paid call.
agent
agent_web_access
Use SML Agent Web Access: give an AI agent one public HTTPS URL and receive compact LLM-ready Markdown through the stable Clean Web Reader service. No separate SML account or API key is required. An unsigned call returns the live x402 PAYMENT-REQUIRED challenge and never auto-spends; retry only with a challenge-specific payment_signature.
call
call_capability
Call a concrete SqueezeOS REST path on the canonical public host. GET is read-only. POST requires confirm_write=true. If the target returns 402 and no payment_signature was supplied, this tool preserves PAYMENT-REQUIRED and returns the closest no-spend SML alternative from the Capability Router. Retry the original route only with a challenge-specific payment_signature. Sensitive operator/control routes and arbitrary auth headers are not exposed.
capability
capability_manifest
Return the current machine capability manifest generated from the running Flask route table. This is the canonical product-inventory authority for MCP discovery.
compare
compare_capabilities
Compare 2-5 live capabilities using the same real metadata returned by inspect_capability; no fabricated composite score is produced.
discover
discover_capabilities
Search the live SqueezeOS capability inventory. Lexical mode is always available; unified mode may add configured evidence-backed semantic/graph context without fabricating scores.
inspect
inspect_capability
Inspect one live capability by sml_id. Returns its real endpoint/payment metadata and, when safe, a real liveness probe rather than an invented reliability score.
recommend
recommend_capability
Return the best matching real SqueezeOS capabilities for a natural-language need, including live endpoint/payment metadata and next actions.
system
system_status
Read the live SqueezeOS status endpoint. The MCP server does not synthesize cluster-health or synchronization claims.
Tools removed
Tools this server used to expose. Anything built against them stopped working on the day they went.
rwa_intelligence
removed 8 Aug 2026
rwa_proof_of_reserves
removed 8 Aug 2026
rwa_scan
removed 8 Aug 2026
rwa_valuation
removed 8 Aug 2026
bureau_public_score
removed 23 Aug 2026
get_invoice
removed 23 Aug 2026
verify_payment
removed 23 Aug 2026
agentbids_discover
removed 31 Aug 2026
agent_economy
removed 31 Aug 2026
agent_routes_discover
removed 31 Aug 2026
audit_information_gain
removed 31 Aug 2026
autopilot_start
removed 31 Aug 2026
autopilot_status
removed 31 Aug 2026
autopilot_stop
removed 31 Aug 2026
autopilot_trades
removed 31 Aug 2026
bazaar_negotiator_discover
removed 31 Aug 2026
beastmode_scan
removed 31 Aug 2026
build_entity_schema
removed 31 Aug 2026
capabilities_feed
removed 31 Aug 2026
ccs_info
removed 31 Aug 2026
ccs_leaderboard
removed 31 Aug 2026
ccs_report
removed 31 Aug 2026
ccs_score
removed 31 Aug 2026
ccs_stats
removed 31 Aug 2026
ccs_validate
removed 31 Aug 2026
circuit_breaker_reset
removed 31 Aug 2026
citation_score
removed 31 Aug 2026
convergence_check
removed 31 Aug 2026
council_verdict
removed 31 Aug 2026
demo_council
removed 31 Aug 2026
extract_aeo_blocks
removed 31 Aug 2026
fred_preview
removed 31 Aug 2026
fred_series
removed 31 Aug 2026
futures_browse
removed 31 Aug 2026
futures_create
removed 31 Aug 2026
futures_leaderboard
removed 31 Aug 2026
futures_take
removed 31 Aug 2026
generate_additive_hook
removed 31 Aug 2026
hiring_browse_jobs
removed 31 Aug 2026
hiring_post_job
removed 31 Aug 2026
iam_resolve
removed 31 Aug 2026
iam_truth
removed 31 Aug 2026
inspect_freshness
removed 31 Aug 2026
ipo_price_range_history
removed 31 Aug 2026
ipo_timeline
removed 31 Aug 2026
ipo_upcoming
removed 31 Aug 2026
iwm_odte
removed 31 Aug 2026
knowledge_fabric_query
removed 31 Aug 2026
macro_741_scan
removed 31 Aug 2026
marketplace_browse
removed 31 Aug 2026
marketplace_list_signal
removed 31 Aug 2026
marketplace_read_signal
removed 31 Aug 2026
market_scan
removed 31 Aug 2026
memory_recall
removed 31 Aug 2026
memory_stats
removed 31 Aug 2026
memory_store
removed 31 Aug 2026
mesh_discover
removed 31 Aug 2026
narrative_optimize
removed 31 Aug 2026
options_intelligence
removed 31 Aug 2026
oracle_feeds
removed 31 Aug 2026
oracle_query
removed 31 Aug 2026
post_to_slack
removed 31 Aug 2026
proprietary_ema_signal
removed 31 Aug 2026
provider_score
removed 31 Aug 2026
quick_headline
removed 31 Aug 2026
quick_quote
removed 31 Aug 2026
quick_search
removed 31 Aug 2026
recommend_tool
removed 31 Aug 2026
robinhood_rwa_intelligence
removed 31 Aug 2026
semantic_gaps
removed 31 Aug 2026
settlement_browse
removed 31 Aug 2026
settlement_create
removed 31 Aug 2026
settlement_trigger
removed 31 Aug 2026
signal_history
removed 31 Aug 2026
signal_preview
removed 31 Aug 2026
sovereign_365
removed 31 Aug 2026
sovereign_741
removed 31 Aug 2026
sovereign_full
removed 31 Aug 2026
sovereign_triplelock
removed 31 Aug 2026
truth_verify
removed 31 Aug 2026
try_capability
removed 31 Aug 2026
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://squeezeos-api.onrender.com/mcp | streamable-http | answering | 675 ms | 6 min ago |
Alternatives to SqueezeOS — Institutional AI Market Intelligence
same job, measured the same wayHorus Flow MCP
by horustechltd
Institutional crypto & equity orderflow intelligence for AI trading agents.
DPX — Institutional Cross-Border Settlement
by untitledfinancial
AI-native settlement rail + intelligence oracle for autonomous agents. x402, Base mainnet, 81 tools.
Moltalyzer MCP
by jcislo
Polymarket prediction-market intelligence + AI, GitHub & narrative feeds for agents, via x402.
I
Agentic AI
by anthonywlicausi
Deal intelligence for agents: SEC-verified financials, validation, institutional deal scoring.
X402 MCP Server
by kten-agent
MCP server for Hermes Asia x402 CN/JP market intelligence via USDC on Base. 8 endpoints.
Compound Interesting — market intelligence
by compoundinterest
Source-backed US market signals: insider filings, Congress trades, institutions, consensus.
A
CryptoPulse Data API
by saascloud
Pay-per-call crypto market intelligence for AI agents. USDC on Base via x402.
Oblique Markets
by oblique-api
x402-paid analytics, market intelligence, research, and LLM inference for AI agents.
SqueezeOS — Institutional AI Market Intelligence — questions
Answers built from our own checks of this server.
What can SqueezeOS — Institutional AI Market Intelligence do?
It exposes 15 tools, read directly from the server on our last check. Among them: aftersearch_accept, aftersearch_quote, aftersearch_resolve, aftersearch_verify_serp, agent_web_access, call_capability and 9 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
What is SqueezeOS — Institutional AI Market Intelligence mostly used for?
Its tools cluster around aftersearch and x402. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is SqueezeOS — Institutional AI Market Intelligence working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 89 of 92 checks got a reply (96.7%), average response time 310 ms. The bar chart above shows every period we have measured.
Did SqueezeOS — Institutional AI Market Intelligence ever remove tools?
Yes. rwa_intelligence, rwa_proof_of_reserves, rwa_scan, rwa_valuation and 77 more are no longer exposed — we recorded the date each one disappeared. A tool vanishing usually means a breaking change for anything that depended on it.
Is SqueezeOS — Institutional AI Market Intelligence still maintained?
The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.
How do I connect SqueezeOS — Institutional AI Market Intelligence?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does SqueezeOS — Institutional AI Market Intelligence need an API key?
No. SqueezeOS — Institutional AI Market Intelligence completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 15 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is SqueezeOS — Institutional AI Market Intelligence?
It answers our handshake in 310 ms on average, which is faster than 49% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.