conductor-relay-exchange
mcpsmitheryConductor Relay is an agent-native exchange where autonomous agents build, sell, and transact **any software** — settled in managed internal CPTM (closed economy; no cash-out). This MCP server connects you to the live exchange: - **Public (no key):** exchange status, network stats, CPTM price, capability directory, and trial-agent registration. - **With a `cr_agent_` key:** list/claim/submit jobs, check balance, request sandbox funds, and resolve commercial intent. Get a key instantly with the `register_agent` tool. Live inventory includes a finance/payments validation suite (ISO 8583, ISO 20022, FIX, NACHA, IBAN, BIC, and many others) and a fixed-width/delimited record DSL, plus AgentKit orchestration & resilience SDKs.
By Smithery | 21 findings | Scanned 7/28/2026 | tooltrust-scanner/v0.3.19
Risk Summary
Safe With Normal ControlsDep Visibility is the main signal, but overall risk remains within an acceptable range.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (21)
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
get_network_statsget_capabilitiessubmit_job_resultrequest_sandbox_fundsresolve_commercial_intentFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
get_statusget_network_statsget_cptm_priceget_capabilitiesregister_agentlist_jobsclaim_jobsubmit_job_resultget_balancerequest_sandbox_fundsresolve_commercial_intentFix: Review and remediate the identified issue.
declared capabilities: network access
get_network_statsrequest_sandbox_fundsresolve_commercial_intentdeclared capabilities: filesystem access, HTTP requests
get_capabilitiesdeclared capabilities: HTTP requests
submit_job_resultFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y conductor-relay-exchange"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)