Overwing
Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.
| Endpoint | https://overwing.ai/mcp (streamable-http) |
|---|---|
| Registry version | 0.15.0 |
| Now | 41 tools · grade C (65) · pin ts_baada05deac6f641ebb379f56ab5baeb · protocol 2025-06-18 |
| First / last listed | 2026-10-26 04:26 UTC / 2026-10-26 04:26 UTC |
| Grade over time | 2026-10-26: C (65), 41 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: evaluate evaluate_batch list_rule_sets get_rule_set create_rule_set get_evaluation list_evaluations get_usage whoami create_account prove_domain verify_domain list_plans atlas_lookup atlas_agents atlas_register_agent atlas_verify_registration atlas_list_registrations atlas_withdraw_registration atlas_summary beacon_start beacon_report feedback beacon_sample preflight_payment preflight_check preflight_verdict preflight_report preflight_record preflight_overview tower_load_template tower_create_agent tower_list_agents tower_revoke_agent tower_capabilities tower_decide tower_submit_action tower_get_action tower_compensate tower_get_receipt tower_verify_receipts
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) against an Overwing rule set. The text can be in any language; tested in Spanish, Portuguese, French, German, Japanese, Chinese, Korean, Arabic and Hindi. Results com params: 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. params: items*, rule_set, context, store |
list_rule_sets | List the prebuilt and custom rule sets available to this organization. Needs an organization key. params: include_inactive |
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. params: slug* |
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 review) that callers should take when it fails. Rule instructions may reference `context.*` fields that callers pass with each evaluation. Needs an organization k params: name*, slug*, description, rules* |
get_evaluation | Fetch a stored evaluation by id, including the original input and per-rule results. Needs an organization key. params: id* |
list_evaluations | List recent evaluations, newest first, with optional verdict and rule set filters. Use next_cursor to page. Needs an organization key. params: limit, verdict, rule_set, cursor |
get_usage | Daily usage, remaining quota for today, and plan limits. Needs an organization key. params: days |
whoami | Identify the organization and plan behind the API key on this request, the key's scope, the organization's data settings (store_inputs, retention_days), and whether billing is set up. Needs an organization key. params: none |
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 key (whoami says which account a key belongs to). The key is the account, so store it at once: with no email there is no reset link. It starts at 50 evaluation params: org_name, use_for_session |
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 publish at the domain, as a DNS TXT record or as a file under /.well-known; then call verify_domain. One domain belongs to one account. Calling again for the same params: domain* |
verify_domain | Look for the value prove_domain asked for, at the domain. Found: the domain is the account's. Not found: an error saying what was looked for; DNS changes can take a few minutes, and calling again is safe. Needs an organization key. params: none |
list_plans | Public plan catalog: prices, daily limits, and per-minute burst limits. No API key needed. params: none |
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 Auth signature, user-agent string only, or unattributable) and a trust note. Works with no API key: 10 lookups a day. With a key, metered per day by Atlas tier: params: user_agent* |
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, evasion flags and traffic shares. Filter by free text, purpose (training, search, browser, coding), operator, or verification. Needs an organization key. params: q, purpose, operator, verification, limit |
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 token the User-Agent carries (the product name, such as AcmeBot). The answer carries one value to publish at that domain, as a DNS TXT record or as a file under /.w params: name*, operator*, domain*, tokens*, purpose, user_agent, description, policy_url, key_directory_url, follows_robots_txt |
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 found: an error saying what was looked for; DNS changes can take a few minutes, and calling again is safe. Needs an organization key. params: id* |
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 key. params: none |
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. params: id* |
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 summary of the Agent Consumers report on what agents actually spend. No key needed. params: none |
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, OpenAPI discovery, and how the home page reads to a model, then returns three answers (find, read, use), a score and the fixes worth making. This tool starts a params: url* |
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 when it did not pass, and top_fixes ranked by value. With no key, the summary of the same report: score, verdict, the three answers and the first fix (access=sum params: id* |
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; give a contact if you want an answer. No key needed. params: message*, about, evaluation_id, contact |
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. params: none |
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 x402-list's directory (verified delivery, recorded settlements, buyers, shared payout addresses) and the server's own /.well-known/x402 manifest, and the price params: payment_required*, requested_url, network, policy |
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) and answers allow or refuse against your policy, with every reason. Sign only if decision is "allow". Treat a refusal, an error, or anything else as do not sign. params: transaction*, policy* |
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 transaction. No key needed. params: id* |
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 permitted. The outcome is published. A covered miss is paid to the wallet in the verdict, never to whoever reported it. No key needed. params: id*, signature* |
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 key needed. params: none |
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 needed. params: none |
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 organization key. Returns a sample input you can submit. Next: tower_create_agent. params: none |
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 server does not keep it: store it, and send it as the Authorization bearer on a connection used for the agent tools (tower_capabilities, tower_decide, tower_submit_ params: name*, scopes*, use_for_session |
tower_list_agents | List this organization's Tower agents with scopes, status and last use. Keys are never returned. Needs an organization key. params: none |
tower_revoke_agent | Revoke an agent. Its key stops working at once and cannot be restored. Needs an organization key. params: agent_id* |
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. params: none |
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. params: operation*, input* |
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 stable for this business request, such as the source message id: repeating a key returns the original outcome instead of acting twice. Set dry_run to see the deci params: operation*, input*, idempotency_key*, dry_run |
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. params: action_id* |
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. params: 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. params: id* |
tower_verify_receipts | Recompute every hash and check every signature over a range of this organization's receipts. Reports the first break, if any. Defaults to the whole chain (up to 5,000 links per call). Needs an agent key. params: from, to |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.