ComputeLedgerSAFE
CLI, library, and MCP server for signing, hash-chaining, and verifying compute usage receipts across any provider.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/RudrenduPaul/ComputeLedger/actions/workflows/ci.yml) [](https://www.npmjs.com/package/computeledger-cli) [](https://pypi.org/project/computeledger-cli/) [](LICENSE) [](package.json)
Install • Quickstart • Features • CLI reference • Comparison • FAQ
Sign, hash-chain, and independently verify compute usage, portable across any provider.
ComputeLedger records a compute job's usage (GPU-hours, hardware, duration, workload type) as a cryptographically signed receipt and appends it to a tamper-evident local ledger. Anyone can verify a receipt's authenticity and the ledger's integrity without trusting the issuer, and without buying into any single cloud, chain, or ve
324983478a56OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add computeledger-cli -- uvx computeledger-cli==0.1.4 computeledger mcp
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (8)
raw_key = base64.b64decode(public_key_raw_base64, validate=True)
signature = base64.b64decode(signature_base64, validate=True)
signature = sign_bytes(key_pair.private_key_pem, bytes.fromhex(digest_hex))
payload.get("publicKey", ""), bytes.fromhex(receipt["hash"]), receipt.get("signature", "")raw = base64.b64decode(kp.public_key_raw_base64)
@modelcontextprotocol/sdk, zod, @types/node, @vitest/coverage-v8, eslint, typescript, typescript-eslint, vitest
docs/demo-export-ledger.gif
Gates applied: no_behavioural_pass.
324983478a56full audit observations/trust-audit/mcp-server/rudrendupaul__computeledger.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 324983478a56 | SAFE | B | 89 | first audit |
Questions
What is the ComputeLedger MCP server?
CLI, library, and MCP server for signing, hash-chaining, and verifying compute usage receipts across any provider.
Is ComputeLedger safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does ComputeLedger need?
No credential environment variables were found in its source, so it appears to need none.
How does ComputeLedger run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as computeledger-cli at 0.1.3.
How current is this page?
The grade is for one exact copy of the source (324983478a56), read on 2026-10-11. The repository is watched and re-audited when it changes.