com.decionis/mcp
NPM · @DECIONIS/MCP · 2 COMPONENTS
Authorize consequential AI agent actions before execution
Available components
Last scanned (20 hours ago)
Scores higher than 80% 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 Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 13 of 48 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 37 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability77
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 1063 tokens (~96/item across 11 items; 11 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 Coverage87
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 62% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 11 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 (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
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
- 17 Oct 26 +2
- Stability: 0.87 → pass security
- 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.
- 15 Oct 26 −3
- Stability: pass → 0.83 functional
- 14 Oct 26 +1
- Stability: 0.97 → pass security
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/@decionis/mcp@0.3.0
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 →
Dependencies 48 packages
| Packages resolved | 48 |
|---|---|
| Stale | 13 |
| 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 →
decionis_demo Run the One-Minute Demo ~104
See Decionis work in under a minute: runs four canned intents (refund within limit, refund over limit, deploy during a change freeze, an action no rule covers) through the real protocol evaluator with a built-in sample policy. Entirely local — no account, no API key, no network, no policy file needed, nothing recorded. Call this on first contact with Decionis; use decionis_evaluate to gate this repo's own actions afterwards.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
decionis_evaluate Evaluate Candidate Action Locally ~294
Evaluate a candidate action against the repo's DECIONIS_POLICY.md — or, with policy_pack, against one of the Decionis policy packs (decionis_list_policy_packs) — through the real Decionis protocol evaluator, entirely locally (no network, no credentials, nothing recorded). The exact policy version is pinned on every call; an unavailable version fails closed rather than silently deciding under another bundle. Call this BEFORE committing, deploying, migrating, or any risky action, and abide by the verdict: allow → proceed; block → do not proceed; review/escalate → stop and involve a human (an ESCALATE in enforce mode returns an evaluation_id that decionis_request_presence_verification can resolve when Presence is configured).
| Name | Type | Req | Description |
|---|---|---|---|
| mode | string | – | Default: shadow. |
| path | string | – | Policy file path override. |
| payload | object | yes | The candidate action, e.g. {"action": "production-deploy", "change_freeze": true, "agent_generated": true} |
| policy_pack | string | – | Evaluate under a named Decionis policy pack (a key from decionis_list_policy_packs, e.g. finance, devops, sap) instead of the repository policy file. The pack's bundle is seeded into the local evalua… |
| workflow_key | string | – | Optional workflow key for the gated surface. |
No output schema declared.
No examples provided.
decionis_list_policy_packs List Decionis Policy Packs ~101
List the policy packs the Decionis evaluator ships — finance, devops, sap, salesforce, workday, hospitality and the workflow overlays — with each pack's key, description, default decision domain and exact bundle version. Pass a key as policy_pack to decionis_evaluate to decide under that pack instead of the repository policy file. Entirely local: the catalogue is read from the in-process protocol, nothing is fetched.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
decionis_read_policy Read Repository Policy ~92
Read and compile the repo's DECIONIS_POLICY.md execution policy: path, sha256, and the enforceable rules (name, verdict, priority, domain) or compile errors. Use this to learn what this repository allows, blocks, restrains, or escalates.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | – | Policy file path (default: $DECIONIS_POLICY_PATH or ./DECIONIS_POLICY.md) |
No output schema declared.
No examples provided.
decionis_verdict_help Explain Decionis Verdicts ~45
Reference for Decionis verdicts (allow/block/restrain/escalate), the rules-block grammar and operators, and how an agent should behave on each verdict.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
shield.check_spending_authority Check Shield Spending Authority ~111
Check spending authority for an app or AI agent before taking the consequential action.
| Name | Type | Req | Description |
|---|---|---|---|
| agentId | string | – | Registered agent identity, when an agent is spending. |
| amount | number | yes | Amount in major currency units. |
| category | string | – | – |
| currency | string | yes | ISO 4217 currency code. |
| merchant | string | – | – |
| metadata | object | – | – |
| purpose | string | yes | Clear user-facing reason for spending. |
| transactionType | string | – | – |
No output schema declared.
No examples provided.
shield.get_decision Get Shield Decision ~34
Retrieve the current ALLOW, ASK, or BLOCK decision and its evidence identifiers.
| Name | Type | Req | Description |
|---|---|---|---|
| decisionId | string | yes | – |
No output schema declared.
No examples provided.
shield.get_permission Get Shield Permission ~23
Read the spender identity and user-owned limits bound to this Shield credential.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
shield.pair Pair with the user's Shield ~107
Bind this assistant to the user's Decionis Shield with the six-character pairing code shown in the Shield app (AI spending allowance → Bind your own agent). Ask the user for the code; never guess one. After pairing, shield.request_purchase and the other shield.* tools ask the user's own spending rules.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | The code from the Shield app. |
| displayName | string | – | How the Shield app should list this assistant (default: the client and this computer). |
No output schema declared.
No examples provided.
shield.request_approval Request Shield Approval ~37
Start or poll Presence approval for an ASK decision. Do not execute while the verdict remains ASK.
| Name | Type | Req | Description |
|---|---|---|---|
| decisionId | string | yes | – |
No output schema declared.
No examples provided.
shield.request_purchase Request Shield Purchase Authorization ~115
Ask the user's Shield for ALLOW, ASK, or BLOCK before a purchase. Execute only on ALLOW.
| Name | Type | Req | Description |
|---|---|---|---|
| agentId | string | – | Registered agent identity, when an agent is spending. |
| amount | number | yes | Amount in major currency units. |
| category | string | – | – |
| currency | string | yes | ISO 4217 currency code. |
| merchant | string | – | – |
| metadata | object | – | – |
| purpose | string | yes | Clear user-facing reason for spending. |
| transactionType | string | – | – |
No output schema declared.
No examples provided.
How do I install the com.decionis/mcp server?
com.decionis/mcp runs locally as an npm package, launched with npx -y @decionis/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 · @decionis/mcp
claude mcp add com-decionis-mcp -- npx -y @decionis/mcp
What is the com.decionis/mcp server?
com.decionis/mcp is listed in the public MCP registry as com.decionis/mcp. Authorize consequential AI agent actions before execution. This page covers its npm package (@decionis/mcp).
Is the com.decionis/mcp server safe to use?
com.decionis/mcp scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting 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 com.decionis/mcp server expose?
com.decionis/mcp exposes 11 tools: decionis_read_policy, decionis_evaluate, decionis_list_policy_packs, decionis_demo, decionis_verdict_help, and 6 more. Their descriptions and schemas cost roughly 1,063 tokens of context every time the server is loaded.
Is the com.decionis/mcp server still maintained?
com.decionis/mcp 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 com.decionis/mcp server under?
com.decionis/mcp 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 com.decionis/mcp server?
VerifyMCP ran 16 checks on com.decionis/mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. 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.