Connect Agent Enhancer

Add one free, no-auth reliability sidecar to an existing agent. Keep the agent you already use; call these tools only when planning, coordination, recovery, or evidence will help.

Remote MCP

Copy a tested boundary

Live status →

These links carry a privacy-safe source label so aggregate initialization and invocation health can be measured. Prompts, tool arguments, credentials, and wallet details are not collected for attribution.

Contract-tested

MCP-compatible agents

3 progressive tools discover and invoke 24 modules.

 

Connection guide →
Contract-tested

ChatGPT

37 direct tools across the same 24 modules.

 

Connection guide →
Contract-tested

Claude

37 direct tools across the same 24 modules.

 

Connection guide →

Access

Free beta today

USDC not accepted

Every public module is free today. Optional higher-volume x402 execution is staged but inactive.

Public modules
24
Free today
24 of 24
Payment mode
disabled
USDC accepted now
No

Claude and ChatGPT connectors

All public modules appear as direct, no-auth tools at /mcp/claude and /mcp/chatgpt. Each exposes 37 direct tools across 24 modules and has a separate 60-call-per-client, 600-call-global minute budget plus lower per-module limits.

Connector setup →

What remains free

Discovery, schemas, status, validation, unsupported lookups, capability requests, and bounded connector access remain free. Connectors do not collect or transfer payment.

Documentation →

Future higher-volume execution

A later vendor-neutral HTTP request may buy capacity under explicit Base USDC terms. It will not hide better answers. Prices, limits, receiver, replay, and refund terms must be published before activation.

Not active

Compatibility evidence

Effectiveness evidence →
SurfacePublic boundaryVerificationDistribution status
MCP-compatible agents3 progressive tools discover and invoke 24 modulesAutomated protocol, contract, discovery, and hosted boundary checksPublished in the Official MCP Registry
ChatGPT37 direct tools across the same 24 modulesAutomated contract and hosted boundary checks; human review materials preparedPublic endpoint; marketplace review is not claimed
Claude37 direct tools across the same 24 modulesAutomated contract and hosted boundary checks; host review remains separatePublic endpoint; directory approval is not claimed
Codex and skills-compatible agentsRepo-scoped skill; no persistent MCP; direct HTTP only after local risk selection200-run preregistered Codex publication passed; safety gains appeared in overlapping workers and stale scheduled refreshesSkills-only archive and source are published on GitHub

Contract-tested means the published protocol boundary, schemas, and hosted behavior passed the project's automated checks. It does not imply approval by a host marketplace or directory.

Open source

Use the package on GitHub

Open repository →

Remote MCP configuration

Start with this common JSON shape and adapt the surrounding configuration filename to your MCP host.

 

Inspect the versioned manifest →

Agent Skills

List the seven workflow skills before choosing which ones to install.

 

Inspect all skills →

Proof before promotion

Public claims are tied to reproducible checks. Review the live effectiveness report, measurement methodology, and security policy. New framework and marketplace names are added to this page only after their integration is reproducible.