three.ws Provenance
NPM · @THREE-WS/PROVENANCE-MCP
Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
Available components
Last scanned (8 hours ago)
Scores higher than 48% of npm servers
Category Crypto and Web3
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 31 of 102 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 54 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability65
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1013 tokens (~337/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management73
- Stability observed for 22 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 −4
- Stability: pass → 0.73 functional
- 30 Oct 26 +1
- Stability: 0.97 → pass security
- 29 Oct 26 −1
- Stability: pass → 0.97 functional
- 24 Oct 26 −5
- CVE-2023-54404 affects this package: high ▼ security
- Known CVEs: pass → fail ▼ security
- 17 Oct 26 +1
- Stability: 0.97 → pass security
- 15 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Oct 26 +42
- Injection markers: unverified → pass ▲ security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Stability: unverified → 0.90 ▲ functional
- Package version: 0.1.2 → 0.1.3 functional
- 12 Oct 26 +15
- Malware scan: unverified → pass ▲ security
- Package version: 0.1.2 → 0.1.3 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed npm/@three-ws/provenance-mcp@0.1.3
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 102 packages
| Packages resolved | 102 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
append_agent_action Append a signed action to the provenance ledger ~361
Record an action in an agent's append-only provenance ledger — the permanent, auditable trail of what the agent did. Provide `agent_id` (THREE_WS_TOKEN must own it), a short `type` (≤64 chars, e.g. launch, buy, post, reflect), an optional structured `payload`, and an optional `source_skill`. WRITE ACTION: this APPENDS a new immutable record — it can never be edited or deleted, and calling it twice records two distinct actions, so don't retry blindly. When an EVM signer is configured (THREE_WS_SIGNER_KEY env or the `signer_key` arg) the action is ERC-191-signed before sending, making its authorship publicly verifiable; with no key it is appended unsigned. Returns the stored record (with id + created_at) and a `signing` block reporting whether it was signed and by which address.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The agent identity uuid to record the action under. Your token must own it. |
| payload | object | – | Structured details of the action (any JSON object) — e.g. { mint, amount_sol, signature }. Stored verbatim and covered by the signature. |
| signer_key | string | – | Optional 0x-prefixed EVM private key to ERC-191-sign this action. Overrides THREE_WS_SIGNER_KEY for this call. Omit to use the env key, or sign nothing if none is set. |
| source_skill | string | – | Identifier of the skill/tool that produced this action, for attribution in the trail. |
| type | string | yes | Short action type, e.g. launch, buy, sell, post, reflect, follow. Truncated to 64 chars server-side. |
No output schema declared.
No examples provided.
list_agent_actions List an agent's action-provenance trail ~253
Read an agent's append-only action log, newest-first, cursor-paginated. Returns each action's id, type (e.g. launch, buy, post, reflect), payload, source_skill, created_at, and — when the action was signed — its ERC-191 signature + signer_address. Each record is checked against its own signature: `verification.reason` is `ok` (recovered signer matches the claimed address), `unsigned`, `signer_mismatch` (recovered a different address — tampering OR an action signed under a different canonical scheme; treat as unverified, not trusted), or `malformed_signature`. Pass the returned `next_cursor` back as `cursor` to page further. The ledger is owner-scoped: THREE_WS_TOKEN must own `agent_id`. Read-only; the log is immutable so older pages never change.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The agent identity uuid whose provenance trail to read. Your token must own it. |
| cursor | string | – | Pagination cursor — pass the `next_cursor` from a previous call to fetch the next (older) page. |
| limit | integer | – | Max actions to return (1–200, default 50). |
No output schema declared.
No examples provided.
query_action Fetch + verify one provenance action ~218
Fetch a single action from an agent's append-only log by its id, then verify it. Returns the action (type, payload, source_skill, created_at, signature, signer_address) plus a `verification` block: `signed`, `valid`, `reason` (`ok` | `unsigned` | `signer_mismatch` | `malformed_signature`), the `recovered` signer address, and the recomputed `digest`. `valid:true` means the ERC-191 signature recovers to the claimed signer over the canonical action form — cryptographic proof the named agent authored this exact action and it was not altered. The ledger is owner-scoped: THREE_WS_TOKEN must own `agent_id`. Returns ok:false / not_found when the id is absent from this agent's log. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The agent identity uuid that owns the action. Your token must own this agent. |
| id | string | yes | The numeric action id to fetch (the `id` field from list_agent_actions). |
No output schema declared.
No examples provided.
How do I install the three.ws Provenance MCP server?
three.ws Provenance runs locally as an npm package, launched with npx -y @three-ws/provenance-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @three-ws/provenance-mcp
claude mcp add nirholas-provenance-mcp -- npx -y @three-ws/provenance-mcp
What is the three.ws Provenance MCP server?
three.ws Provenance is an MCP server listed in the public MCP registry as io.github.nirholas/provenance-mcp. Append-only, signed, on-chain-verifiable agent action log, record and audit what agents did. This page covers its npm package (@three-ws/provenance-mcp).
Is the three.ws Provenance MCP server safe to use?
three.ws Provenance scores 74 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the three.ws Provenance MCP server expose?
three.ws Provenance exposes 3 tools: list_agent_actions, query_action, append_agent_action. Their descriptions and schemas cost roughly 832 tokens of context every time the server is loaded.
Is the three.ws Provenance MCP server still maintained?
three.ws Provenance is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the three.ws Provenance MCP server under?
three.ws Provenance declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.