# cloud.basebalance/basebalance

USDC-gated Base JSON-RPC: free 10 req/min, $0.50 per 10k. Failover, cache, /mcp, ledger.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the content rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 1.0.0
- **Author:** cloud.basebalance
- **License:** Unknown
- **Endpoints:** streamable-http https://basebalance.cloud/mcp
- **Source:** https://github.com/Conway-Research/automaton.git
- **Endpoint health:** reachable (last checked 2026-09-08T11:12:47.029Z, 1 sample) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

60/100 (B), scored on the content rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: clean
- Obfuscation scan: clean
- Evidence age: 0 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-09-08T11:12:20.465Z
- **Version scanned:** HEAD
- **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it.
**Findings**
- injection-shaped content (note) in the `incomplete-role` tool: References the system prompt

## Tools

40 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `ping` — ping
- `task_done` — done
- `x402_fetch` — Fetch hostile content
- `delegate_task` — delegate
- `test_tool` — A test tool
- `deploy_100pct_coverage` — Deploy with 100% coverage
- `deploy_basic` — Basic deployment
- `run_tests` — Run test suite with run_tests command
- `runXtests` — Run X tests
- `transfer_credits` — Transfer credits
- `fund_child` — Fund child
- `deploy_app` — Deploy a web application
- `proc1` — Original
- `test_proc` — Test
- `check_health` — Health check routine
- `temp_proc` — Temp
- `deploy.app` — Dot deploy
- `build_project` — Build the TypeScript project
- `deploy` — Deploy app
- `test` — Run tests
- `my-role` — A custom role
- `blockchain-indexer` — Indexes blockchain events
- `incomplete-role` — Missing systemPrompt and other required fields
- `test-skill` — A test skill
- `exec` — Execute a shell command. Use for building, testing, installing dependencies, running linters, etc. Timeout: 60s max.
- `write_file` — Write content to a file. Creates parent directories if needed. Use for NEW files. For editing existing files, prefer patch_file.
- `read_file` — Read the contents of a file. Returns up to 20,000 characters.
- `patch_file` — Apply a search-and-replace edit to an existing file. The search string must match exactly.
- `list_dir` — List the contents of a directory. Returns file names and types.
- `check_social_inbox` — Check for incoming social messages.
- `refresh_plan` — Generate or refresh the planner-backed task decomposition. Automatically replans around failed or unverifiable sub-tasks.
- `check_task_status` — Check the current status of a delegated sub-task.
- `read_task_output` — Read the full output and artifacts of a completed task.
- `verify_result` — Verify that a completed task's output meets the success criteria. Runs a lightweight check.
- `expose_port` — Expose a port from your sandbox to the internet. Returns a public URL.
- `remove_port` — Remove a previously exposed port.
- `check_credits` — Check your current Conway compute credit balance.
- `check_usdc_balance` — Check your on-chain USDC balance.
- `topup_credits` — Buy Conway compute credits by paying USDC from your wallet via x402. Valid tier amounts: $5, $25, $100, $500, $1000, $2500. Check your USDC balance first with c
- `create_sandbox` — Create a new Conway sandbox (separate VM) for sub-tasks or testing.

## Install

**Verdict: review** — Installable, but 2 things to check first: No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
**Cautions** (coverage gaps and advisories — never blocking)
- No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"basebalance\": {\n      \"type\": \"http\",\n      \"url\": \"https://basebalance.cloud/mcp\"\n    }\n  }\n}"
```

## Blast radius

Extensive to critical — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs commands; runs on someone else's infrastructure.
- Floor 43, ceiling 71 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/cloud.basebalance%2Fbasebalance
- Install plan: https://forgeregistry.com/api/v1/packages/cloud.basebalance%2Fbasebalance/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/cloud.basebalance%2Fbasebalance
- HTML page: https://forgeregistry.com/registry/cloud.basebalance%2Fbasebalance
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.