Silvanexum
NPM · @SILVANEXUM/MCP · 2 COMPONENTS
Spend control for AI agents - cost attribution, budget caps, and signed runs as MCP tools.
Available components
Last scanned (9 hours ago)
Scores higher than 46% of npm servers
Category AI and Machine Learning
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
- 30 of 94 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- 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 5 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability78
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 727 tokens (~72/item across 10 items; 10 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
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 Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "deploy_template" implies "deploy" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 10 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
Checks we ran (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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.
- 3 Nov 26 +1
- Stability: 0.97 → pass security
- 2 Nov 26 −1
- Stability: pass → 0.97 functional
- 27 Oct 26 +1
- Stability: 0.97 → pass security
- 26 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
- 20 Oct 26 +1
- Stability: 0.97 → pass security
- 18 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.
- 16 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
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/@silvanexum/mcp@0.4.0
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 94 packages
| Packages resolved | 94 |
|---|---|
| Stale | 30 |
| 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 →
create_budget Create budget ~185
Agent FinOps — create a spend cap over an org / project / agent for a period. With enforcement 'block', a run or mesh hop that would breach the cap is rejected server-side (HTTP 402). Requires a key with write scope.
| Name | Type | Req | Description |
|---|---|---|---|
| alertThresholdPct | number | – | Percent of the cap that flips state to 'warn'. Default 80. |
| enforcement | string | – | 'block' rejects a breaching run/hop (HTTP 402); 'alert' only warns. Default block. |
| limitCredits | number | yes | Spend cap in credits for the period. |
| name | string | yes | Human label for the budget. |
| periodType | string | yes | Reset cadence for the cap. |
| scopeId | string | – | The project/agent id — required unless scopeType is 'org'. |
| scopeType | string | yes | What the cap applies to. |
No output schema declared.
No examples provided.
deploy_template Deploy template ~71
Deploy a 1-click vertical agent template into a ready, signed agent (M11). Note: template endpoints may be 'planned' / not yet live on a given deployment.
| Name | Type | Req | Description |
|---|---|---|---|
| params | object | – | Template parameter values (key → value). |
| templateId | string | yes | The template id to deploy. |
No output schema declared.
No examples provided.
get_agent Get agent ~30
Fetch an agent's configuration and earned reputation by id.
| Name | Type | Req | Description |
|---|---|---|---|
| agentId | string | yes | The agent id. |
No output schema declared.
No examples provided.
get_reputation Get reputation ~43
Get an agent's earned reputation — volume-aware trust score, success rate, and confidence, derived from signed runs.
| Name | Type | Req | Description |
|---|---|---|---|
| agentId | string | yes | The agent id. |
No output schema declared.
No examples provided.
get_run Get run ~42
Fetch a run's full signed trace (the step-by-step model/tool/agent timeline) by id.
| Name | Type | Req | Description |
|---|---|---|---|
| runId | string | yes | The run/execution id. |
No output schema declared.
No examples provided.
get_spending Get spending ~116
Agent FinOps — cost attribution. Spend rolled up by a dimension (agent / project / model / provider) over a time window, from real run telemetry + the mesh ledger. Read-only. Answers 'which agent/model burned the budget?'.
| Name | Type | Req | Description |
|---|---|---|---|
| groupBy | string | – | Dimension to attribute spend by. Default: agent. |
| since | string | – | Window start — relative ('-7d', '-24h') or ISO. Default -30d. |
| to | string | – | Window end — ISO. Default now. |
No output schema declared.
No examples provided.
list_budgets List budgets ~56
Agent FinOps — list spend caps (budgets), each with its live computed spend, remaining, and state (ok / warn / exceeded) for the current period.
| Name | Type | Req | Description |
|---|---|---|---|
| scopeType | string | – | Filter budgets by scope. |
No output schema declared.
No examples provided.
run_agent Run agent ~77
Run an agent on a prompt. The run is captured, secret-scrubbed, and cryptographically signed. Returns the answer plus a replayable, signed trace URL. Requires the `run` scope.
| Name | Type | Req | Description |
|---|---|---|---|
| agentId | string | yes | The agent id to run. |
| prompt | string | yes | The input/instruction for the agent. |
No output schema declared.
No examples provided.
search_agents Search agents ~88
Search the Silvanexum marketplace for agents, ranked by PROVEN OUTCOMES (real run corpus + reputation), not stars. Returns proof-ranked listings.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Filter by listing category. |
| q | string | – | Free-text query, e.g. 'legal contract review'. |
| sort | string | – | Ranking. Default: proof (by signed-run corpus + reputation). |
No output schema declared.
No examples provided.
wallet_balance Wallet balance ~19
Get the org's credit balance and recent ledger activity.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
How do I install the Silvanexum MCP server?
Silvanexum runs locally as an npm package, launched with npx -y @silvanexum/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 · @silvanexum/mcp
claude mcp add silvanexum-silvanexum -- npx -y @silvanexum/mcp
What is the Silvanexum MCP server?
Silvanexum is an MCP server listed in the public MCP registry as io.github.silvanexum/silvanexum. Spend control for AI agents - cost attribution, budget caps, and signed runs as MCP tools. This page covers its npm package (@silvanexum/mcp).
Is the Silvanexum MCP server safe to use?
Silvanexum scores 73 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 Silvanexum MCP server expose?
Silvanexum exposes 10 tools: search_agents, get_agent, get_reputation, run_agent, get_run, and 5 more. Their descriptions and schemas cost roughly 727 tokens of context every time the server is loaded.
Is the Silvanexum MCP server still maintained?
Silvanexum 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 Silvanexum MCP server under?
Silvanexum 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.
What did VerifyMCP test on the Silvanexum MCP server?
VerifyMCP ran 15 checks on Silvanexum, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about Silvanexum: Security disclosure. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.