overwing-mcp

MCPcommunity
v0.5.0OverwingMITUpdated 1d agonpmGitHub

Overwing MCP server: guardrails for LLM output. Score any text for safety, quality and compliance and get pass / fail / review verdicts with calibrated confidence, from any MCP-capable agent. Plus Overwing Atlas: identify any User-Agent string against a r

Works in
ClaudeCursorCopilotGemini

Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
698Downloads/wk
1d agoLast update
Needs 1 credential before it runs
  • OVERWING_API_KEYAPI keyrequired

    Overwing API key (ow_live_...). Get one at https://overwing.ai/login or POST https://overwing.ai/api/v1/signup

Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.

Package
AuthorOverwing
LicenseMIT
Version0.5.0
Sourcenpm+mcp-registry
Trust Status
B
60/100Good
✓Listed in Forge index+10/10
—Publisher identity verified+0/20
→ Publisher: run `forge publish` from the package repo to claim ownership
—Ed25519 publish signature+0/5
→ Included automatically when the publisher runs `forge publish`
—Domain verification+0/5
→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
—npm Trusted Publishing (Sigstore)+0/5
→ Publish from GitHub Actions with --provenance so the attestation binds this package to this repo
—npm maintainer match+0/5
→ Earned once your identity is verified above and that login is an npm maintainer of this package
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
Dependencies✓ 60 resolved+ · none vulnerable
Tool surface13 tools · none privileged
Security scan✓ Cleanv0.5.0 · todayHow well does this scan work?
EvalsNone
IndexedSep 24, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

13 tools · none privileged
Statically extracted from the published packagev0.5.0 · 5h ago

Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.

evaluateNo description published

This tool published no description. Forge does not invent one.

evaluate_batchScore 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.

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.

No input schema was published for this tool.

list_rule_setsList the prebuilt and custom rule sets available to this organization.

List the prebuilt and custom rule sets available to this organization.

No input schema was published for this tool.

get_rule_setFetch a rule set with its full rule definitions. Use 'content-safety' as a worked example when writing your own.

Fetch a rule set with its full rule definitions. Use 'content-safety' as a worked example when writing your own.

No input schema was published for this tool.

create_rule_setCreate 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 instruct…

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 instruct…

No input schema was published for this tool.

get_evaluationFetch a stored evaluation by id, including the original input and per-rule results.

Fetch a stored evaluation by id, including the original input and per-rule results.

No input schema was published for this tool.

list_evaluationsList recent evaluations, newest first, with optional verdict and rule set filters. Use next_cursor to page.

List recent evaluations, newest first, with optional verdict and rule set filters. Use next_cursor to page.

No input schema was published for this tool.

get_usageDaily usage, remaining quota for today, and plan limits.

Daily usage, remaining quota for today, and plan limits.

No input schema was published for this tool.

whoamiIdentify the organization and plan behind the configured API key, and whether billing is set up.

Identify the organization and plan behind the configured API key, and whether billing is set up.

No input schema was published for this tool.

list_plansPublic plan catalog: prices, daily limits, and per-minute burst limits. No API key needed.

Public plan catalog: prices, daily limits, and per-minute burst limits. No API key needed.

No input schema was published for this tool.

atlas_lookupSay what a User-Agent string claims to be and whether the claim can be trusted, from the Overwing Atlas registry of 241 AI crawlers, fetchers and browser agents. Returns the claimed agent, operator, purpose class, verification method (Web Bot Auth signature, user-agent string only, or unattributabl…

Say what a User-Agent string claims to be and whether the claim can be trusted, from the Overwing Atlas registry of 241 AI crawlers, fetchers and browser agents. Returns the claimed agent, operator, purpose class, verification method (Web Bot Auth signature, user-agent string only, or unattributabl…

No input schema was published for this tool.

atlas_agentsBrowse 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 (t…

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 (t…

No input schema was published for this tool.

atlas_summaryPublic 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…

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…

No input schema was published for this tool.

12 of 13 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

Overwing MCP server: guardrails for LLM output. Score any text for safety, quality and compliance and get pass / fail / review verdicts with calibrated confidence, from any MCP-capable agent. Plus Overwing Atlas: identify any User-Agent string against a r

Keywords
overwingmcpmodel-context-protocolmcp-serverllmguardrailsai-safetycontent-moderationpii-detectiontoxicityagentsclaudecursoropenai
Alternatives
Comparing tool surfaces…

Dependency tree

What one Forge scan resolved from npm metadata on 2026-09-26 — observed resolution, not a publisher declaration.

60 packages resolved · 2 direct · none carrying advisories Resolution stops at depth 4 and 60 packages.

The crawl stopped at the depth-4 limit. Anything below that level was never resolved.

The crawl stopped at the 60-package limit. The rest of the tree was never resolved.

36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)

Declared but not resolved

53 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.

+41 more not listed. The counts by reason above cover all of them.

Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.