dev.agentsurface/docs

MCPcommunitylive
v2.3.0dev.agentsurfaceUnknownUpdated 2d agoGitHub

Search and read the Agent Surface guide to making websites, apps, APIs and CLIs work with AI agents.

Endpoint healthlive
checked 16h ago · 397ms
100% of the last 1 check reached this endpoint
Works in
ClaudeCursorCopilotChatGPTGemini

Inferred from the transports this listing declares (streamable-http). 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 →
1GitHub stars
2d agoLast update
Package
Authordev.agentsurface
LicenseUnknown
Version2.3.0
Sourcemcp-registry
Trust Status
B
60/100Good
✓Listed in Forge index+10/10
—Publisher identity verified+0/30
→ Publisher: run `forge publish` from the repo to claim ownership
—Domain verification+0/10
→ Not currently available for this listing type — the domain-verification check only runs for npm-backed packages today, so this row cannot be earned here yet regardless of what's hosted at the domain.
✓Prompt-injection scan · clean+30/30
✓Obfuscation / exfil scan · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
DependenciesNot audited
Tool surface8 tools · none privileged
Security scan✓ CleanvHEAD · todayHow well does this scan work?
EvalsNone
IndexedSep 27, 2026

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

Tools

8 tools · none privileged
Statically extracted from the published packagevHEAD · 12h 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.

search_docsSearch Agent Surface documentation about agent-readable software, protocols, and tools. Returns page titles, URLs, slugs, and snippets.

Search Agent Surface documentation about agent-readable software, protocols, and tools. Returns page titles, URLs, slugs, and snippets.

No input schema was published for this tool.

get_pageRead an Agent Surface documentation page as Markdown using a slug returned by search_docs. Use index for the documentation home.

Read an Agent Surface documentation page as Markdown using a slug returned by search_docs. Use index for the documentation home.

No input schema was published for this tool.

tool_call_orderVerifies tools are called in the expected order

Verifies tools are called in the expected order

No input schema was published for this tool.

cost_efficiencyToken usage cost (lower is better)

Token usage cost (lower is better)

No input schema was published for this tool.

output_matchFinal output matches expected (if provided)

Final output matches expected (if provided)

No input schema was published for this tool.

create_issueCreate a new issue in the tracker.

Create a new issue in the tracker.

No input schema was published for this tool.

error_demoIntentionally fail to demonstrate error handling.

Intentionally fail to demonstrate error handling.

No input schema was published for this tool.

wait_for_buildPoll and wait for a CI/CD build to complete. Use when you need to monitor long-running build processes. Returns build status, duration, and artifact URLs. Blocks until completion or timeout. This tool polls internally rather than using the io.modelcontextprotocol/tasks extension — reach for that ex…

Poll and wait for a CI/CD build to complete. Use when you need to monitor long-running build processes. Returns build status, duration, and artifact URLs. Blocks until completion or timeout. This tool polls internally rather than using the io.modelcontextprotocol/tasks extension — reach for that ex…

No input schema was published for this tool.

8 of 8 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

Search and read the Agent Surface guide to making websites, apps, APIs and CLIs work with AI agents.

Keywords
mcp
Alternatives
Comparing tool surfaces…

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.