Overwing is a remote MCP server that gives an AI agent 43 tools, among them atlas_agents, atlas_list_registrations, atlas_lookup. It answers at https://overwing.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 23 September 2026; the last check, on 7 November 2026, succeeded.
Guardrails for LLM output: pass / fail / review verdicts with calibrated confidence in under 500 ms.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
atlas_agents | Browse or search Overwing Atlas, the registry of AI crawlers, fetchers and browser agents: name, operator, user-agent tokens, Web Bot Auth key directory, robots.txt behaviour, and (with Atlas Pro or Team) purpose class, verification, evasio Inputs: q, purpose, operator, verification, limit |
atlas_list_registrations | The agents this organization has registered in Overwing Atlas, newest first, each with its status (pending_verification, pending_review, published, rejected) and, while unverified, the value to publish at the domain. Needs an organization k |
atlas_lookup | Say what a User-Agent string claims to be and whether the claim can be trusted, from the Overwing Atlas registry of AI crawlers, fetchers and browser agents. Returns the claimed agent, operator, purpose class, verification method (Web Bot A Inputs: user_agent |
atlas_register_agent | Add an agent or crawler you operate to the Overwing Atlas registry, free, so a site that looks up its User-Agent learns who runs it. Give the agent's name, the operator (the company or person running it), the operator's domain, and the toke Inputs: name, operator, domain, tokens, purpose, user_agent |
atlas_summary | Public numbers from Overwing Atlas: registry counts by purpose and verification, published browser-agent traffic shares, sector field-scan headlines (e.g. how many OSINT sites carry AI-crawler rules or any agent-payable surface), and the su |
atlas_verify_registration | Look for the proof at the operator's domain: the DNS TXT record or the file that atlas_register_agent asked for. Found: the entry is published in the registry, or held for a person when the operator name already belongs to someone. Not foun Inputs: id |
atlas_withdraw_registration | Withdraw a registration. A published entry leaves the registry, so lookups stop naming the agent; an unfinished request is abandoned. This cannot be undone: register again to put it back. Needs an organization key. Inputs: id |
beacon_report | The report for a check started with beacon_start. The first call runs the check. With an Overwing key on the connection: score (0 to 100), verdict (yes, partly, no), the find / read / use answers, every check with what was found and a fix w Inputs: id |
beacon_sample | A real Overwing Beacon report, free: the check of overwing.ai itself, refreshed daily. Read it to see exactly what a full report holds before starting a check. No key needed. |
beacon_start | Overwing Beacon answers one question about a site: is this product reachable by agents? It checks robots.txt rules for AI agents, llms.txt, the sitemap, the MCP server card, hosted MCP endpoint and MCP Registry listing, the A2A agent card, Inputs: url |
cad_create | Makes a real CAD part from a description: a bracket, an enclosure, an adapter, a jig. Overwing writes a parametric script, builds it with a CAD kernel, measures it, checks it against what was asked, and stores a STEP file and STL files for Inputs: prompt, from, params, idempotency_key |
cad_get | With an id from cad_create: the job's status. While it is building, ask again in about 20 seconds. When complete: the title, the script, the measurements, the checks that were run, part_url (a page showing the part in 3D with download butto Inputs: id |
create_account | Create an Overwing account for yourself, with no email: an organization and an API key, returned once. Nothing is sent to anyone. Use it when you have no key and nobody has given you one; do not create a second account if you already have a Inputs: org_name, use_for_session |
create_rule_set | Create a custom rule set with 1 to 25 rules. Each rule is a choice (pick one option), score (position on an ordered scale), or noul (yes/no) question with a fail condition, optional review threshold, weight, and action (block, redact, or re Inputs: name, slug, description, rules |
evaluate | Works with no API key: 10 evaluations a day, inputs up to 2,000 characters, and the text is not stored. With a key: 250 a day and up, inputs up to 100,000 characters, and your own rule sets. Score any text (typically an LLM's output) agains Inputs: input, rule_set, metadata, context, store |
evaluate_batch | Score up to 50 texts against one rule set in a single call. Each item counts as one evaluation. Returns a summary plus per-item verdicts; items can fail independently. Needs an organization key. Inputs: items, rule_set, context, store |
feedback | Send one message to the people who run Overwing: a verdict you think was wrong, an error you could not act on, a payment you could not make, a tool that did not do what its description says. Read by a person, not answered automatically; giv Inputs: message, about, evaluation_id, contact |
get_evaluation | Fetch a stored evaluation by id, including the original input and per-rule results. Needs an organization key. Inputs: id |
get_rule_set | Fetch a rule set with its full rule definitions. Use 'content-safety' as a worked example when writing your own. Needs an organization key. Inputs: slug |
get_usage | Daily usage, remaining quota for today, and plan limits. Needs an organization key. Inputs: days |
list_evaluations | List recent evaluations, newest first, with optional verdict and rule set filters. Use next_cursor to page. Needs an organization key. Inputs: limit, verdict, rule_set, cursor |
list_plans | Public plan catalog: prices, daily limits, and per-minute burst limits. No API key needed. |
list_rule_sets | List the prebuilt and custom rule sets available to this organization. Needs an organization key. Inputs: include_inactive |
preflight_check | Call this before signing any Solana transaction. Overwing Preflight simulates the unsigned transaction against the chain as it is now, works out what it would take from the wallet you name (SOL, tokens, and control of its token accounts) an Inputs: transaction, policy |
preflight_overview | The reference for Overwing Preflight: every policy field, every reason code a refusal can carry, what a verdict does and does not promise, the price, and the terms of the guarantee. Read it once before the first preflight_check. No key need |
preflight_payment | Call this with the 402 you were given, before signing an x402 payment. It reads the terms (network, asset, amount, payee, timeout, resource) and answers allow, review or refuse with reasons: the terms against your policy, the payee against Inputs: payment_required, requested_url, network, policy |
preflight_record | Everything Preflight has said and how it held up: counts of verdicts and misses, every miss with what the chain showed, the latest verdicts, and what the guarantee's reserve holds. Read it before deciding whether to rely on Preflight. No ke |
preflight_report | After a transaction that Preflight allowed has landed, report its signature. Preflight reads the landed transaction from the chain and says whether the allow held: not_a_miss, or miss when it took more from the wallet than the policy permit Inputs: id, signature |
preflight_verdict | The public record of one Preflight verdict: its decision, reason codes, the programs the transaction would run, the transaction's digest, our signature, and every landed transaction reported against it. Never the wallet, the amounts or the Inputs: id |
prove_domain | Begin proving that your account controls a domain. For an account with no email the domain stands in for one: it raises the limits to the normal free tier, opens full Beacon reports, and lets a lost key be replaced. Returns one value to pub Inputs: domain |
tower_capabilities | List the operations this agent is allowed to call, each with the JSON Schema its input must match and its compensating operation. Call this first; build inputs from the schema rather than guessing. Needs an agent key. |
tower_compensate | Run the compensating operation for an executed action, for example cancel the order that create_order made. Runs once; repeating it returns the first outcome. Needs an agent key. Inputs: action_id |
tower_create_agent | Create a scoped agent identity and its key. Needs an organization key. Scope it to the operations the agent needs (for example create_order) rather than * where you can. The key (ow_agent_...) is returned once, in this result, and this serv Inputs: name, scopes, use_for_session |
tower_decide | Ask Tower how it would rule on an operation without doing anything: auto (would execute), review (a person must approve), or reject. Returns the score, the reason, and each policy question's answer. No side effects. Needs an agent key. Inputs: operation, input |
tower_get_action | Status and result of an action: pending, approved, executed, failed, compensated, or rejected. Use it to poll an action that is waiting on human review. Needs an agent key. Inputs: action_id |
tower_get_receipt | Fetch one signed receipt by id or by sequence number: the payload, its hash, the previous link's hash, and the Ed25519 signature. Needs an agent key. Inputs: id |
tower_list_agents | List this organization's Tower agents with scopes, status and last use. Keys are never returned. Needs an organization key. |
tower_load_template | Set up Overwing Tower for this organization by loading the starter workflow: email purchase order to order entry, with create_order, update_order and cancel_order against a mock IBM i system, and a starter policy. Idempotent. Needs an organ |
tower_revoke_agent | Revoke an agent. Its key stops working at once and cannot be restored. Needs an organization key. Inputs: agent_id |
tower_submit_action | Ask Tower to perform an operation on the legacy system. Tower decides: executed (done), pending (a person must approve; poll tower_get_action, do not resubmit), or rejected (do not retry unchanged). Always send an idempotency_key that is st Inputs: operation, input, idempotency_key, dry_run |
tower_verify_receipts, verify_domain, whoami
Every block below points at https://overwing.ai/mcp. Pick your client and copy.
claude mcp add --transport http overwing https://overwing.ai/mcp
{
"mcpServers": {
"overwing": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://overwing.ai/mcp"]
}
}
}{
"mcpServers": {
"overwing": {
"url": "https://overwing.ai/mcp"
}
}
}{
"servers": {
"overwing": {
"type": "http",
"url": "https://overwing.ai/mcp"
}
}
}{
"context_servers": {
"overwing": {
"url": "https://overwing.ai/mcp"
}
}
}{
"mcpServers": {
"overwing": {
"serverUrl": "https://overwing.ai/mcp"
}
}
}{
"mcpServers": {
"overwing": {
"url": "https://overwing.ai/mcp"
}
}
}name: Overwing
version: 0.0.1
schema: v1
mcpServers:
- name: Overwing
type: streamable-http
url: https://overwing.ai/mcp{
"mcpServers": {
"overwing": {
"httpUrl": "https://overwing.ai/mcp"
}
}
}{
"mcpServers": {
"overwing": {
"type": "http",
"url": "https://overwing.ai/mcp"
}
}
}{
"mcpServers": {
"overwing": {
"url": "https://overwing.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Foverwing.ai%2Fmcp&type=streamable_http&id=overwing&name=Overwing
It answered our last check on 7 November 2026 in 199 ms. Over 4 checks since 23 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by overwing.ai and served from overwing.ai, the vendor's own domain: https://overwing.ai/mcp.
43, as returned by the server's own tools/list on 13 November 2026: atlas_agents, atlas_list_registrations, atlas_lookup, atlas_register_agent, atlas_summary, atlas_verify_registration, atlas_withdraw_registration, beacon_report, and 35 more.
It answered our last check on 7 November 2026 in 199 ms. Over 4 checks since 23 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://overwing.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.overwing. Endpoint host: overwing.ai. ARD identifier: urn:air:ai.overwing:mcp:mcp.
First indexed 23 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.