Gluo
Server Details
Free agent tools, no sign-in: browser flows, test inboxes, web extract, site and security scans.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 10 tools
Each tool targets a distinct object+action: budgets (request/get/close), jobs (create/get/list/undo), and services (list/request), with call_api as the execution primitive. The main friction is that request_budget, request_service, and create_job all involve user-approval handoffs, and call_api vs create_job (one call vs multi-step job) could be momentarily confused, though descriptions do clarify the boundaries.
Every tool follows a clean snake_case verb_noun pattern: call_api, request_budget, get_budget, close_budget, create_job, get_job, list_jobs, undo_job, list_services, request_service. Verbs are used consistently for their actions and nouns map predictably to resources.
Ten tools is well within the ideal range and every tool maps to a needed capability: budget lifecycle, job lifecycle, service discovery/requests, and the generic API call. No redundant or filler tools are present.
Budget and job lifecycles are largely covered (request/get/close; create/get/list/undo) with call_api and request_service handling arbitrary operations and gaps. Minor holes exist: no list_budgets to see multiple active budgets and no explicit cancel/pause_job, though undo_job partially mitigates the latter.
Available Tools
10 toolscall_apiCall a Gluo serviceBInspect
Make one call. Leave out budgetId to use the free tier (free operations only, daily allowance). Input must match the operation's schema exactly (extra fields are rejected). Paid calls are charged only if the answer passes Gluo's output check; repeating an identical call shortly after is free.
Inputs: input (required), service (required), operation (required), budgetId.
close_budgetClose an API budgetBInspect
End a budget when the task is done. Returns a signed statement of every call and charge.
Inputs: budgetId (required).
create_jobStart a golive jobAInspect
Hand off a multi-step, multi-day task that golive runs to completion, even after this session ends. Paid or irreversible steps pause for the user's approval through a link. Job types:
launch_domain: Buy a domain, put its DNS on the configured provider, point it at your app, and confirm it resolves and serves HTTPS. Pauses for the user to approve the purchase with their passkey. Can take minutes to hours; the job keeps running after this session ends. launch_domain input: { "domain": "example.com", "target": "my-app.vercel.app or an IPv4 address" }
Inputs: type (required), input (required), email.
get_budgetCheck an API budgetCRead-onlyInspect
Status, spend, remaining amount and per-operation usage of a budget.
Inputs: budgetId (required).
get_jobCheck a golive jobCRead-onlyInspect
Current status of a job, what is blocking it, and what to do next.
Inputs: jobId (required).
list_servicesList callable APIsARead-onlyInspect
Services Gluo runs for agents (site checks, screenshots, domain availability, email setup, dependency vulnerabilities, ...), each with its exact input schema. Operations marked free can be called right away with call_api and no budget, up to a daily allowance. Anything else, or more than the allowance: request_budget first. Say what you're after in lookingFor and the operations that fit are pointed out.
Inputs: lookingFor.
request_budgetAsk the user for an API budgetAInspect
Request a spending budget for specific operations. Ask only for the operations and amount the task needs: the user sees the exact scope, caps and purpose, and calls outside it are refused. The approval link goes to the user, not to you.
Inputs: scope (required), purpose (required), totalMaxUsd (required), perCallMaxUsd (required), +2 more.
request_serviceTell Gluo what you needed but couldn't getAInspect
If a task needs a service, API or action Gluo doesn't offer, describe it in a sentence or two. This is how Gluo decides what to build next. Include roughly what you'd expect it to cost if you know.
Inputs: need (required), task, wouldPayUsdPerCall.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
49 free agent tools: WHOIS, PDF to text, email checks, FX rates, X12 EDI, JSON repair. No API key.
Free no-auth agent tools: URL to markdown, DNS/RDAP, URL & MCP checks, FX, holidays, embed, rerank.
Free agent tools: SEO snapshots, sitemap refresh, Wikipedia collections and saved-page MCP guides.
Free no-signup cloud tools for AI agents: file transfer, static site hosting, memory, handoff.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI agents to run privacy-first network diagnostics (egress IP, proxies, DNS, port checks, security-header audits), handle authentication primitives like TOTP and disposable inboxes, and use developer utilities such as URL-to-markdown reading, webhook inspection, hashing, file/paste sharing, and read-only EVM RPC calls. All tools are free, require no API keys, and operate under a zero-log policy with automatic expiry.163MIT
- AlicenseAqualityCmaintenanceProvides AI agents with free web tools for converting HTML to Markdown, running EU compliance scans, profiling pages, and checking security headers, with no authentication or dependencies.414 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to run domain-intelligence investigations through six free tools: sanctions screening, IP geolocation with VPN/Tor detection, email validation with breach status, company profiling, WHOIS and email-security scoring, and a single-call domain dossier.MIT
- AlicenseAqualityDmaintenancesecurity tools for AI agents: URL safety scanning, prompt injection detection (200+ patterns), email/password breach checks via HIBP, domain & IP reputation analysis, and AI skill supply chain scanning. Free tier (3 calls/day) or pay-per-request with USDC micropayments via x402.932 npm1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.