Akeyless Agentic Runtime Authority
NPM · @AKEYLESS-COMMUNITY/DEVIN-CONNECTOR
Secretless database and cloud access via Akeyless RTA. Credentials never enter the model.
Available components
Last scanned (6 hours ago)
Scores higher than 0% of npm servers
Category Cloud Infrastructure
Recent critical change
CVE-2023-36665 affects this package (2 Sept 2026). See the changelog before you install this server.
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 Security72
- No malware found by supply-chain analysis.Pass
- CVE check failed: an unpatched critical CVE affects this package; the score is capped at 0. See how to fix → View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 123 of 303 dependencies flagged as unhealthy (9 deprecated). 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 (MIT).Pass
- Actively maintained (last published 120 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability55
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 960 tokens (~240/item across 4 items; 4 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 Management77
- Stability observed for 23 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
- All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 5 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 0
- Stability: pass → 0.77 functional
- 24 Oct 26 0
- Stability: 0.97 → pass security
- 23 Oct 26 0
- Stability: pass → 0.97 functional
- 17 Oct 26 0
- Stability: 0.97 → pass security
- 3 Oct 26 0
- Stability: pass → 0.77 functional
- 2 Oct 26 0
- Stability: 0.97 → pass security
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 26 Sept 26 0
- Stability: pass → 0.80 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/@akeyless-community/devin-connector@0.1.0
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 43 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-5375-pq7m-f5r2 | CVE-2026-48068 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-7v5v-9h63-cj86 | CVE-2024-37168 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| GHSA-99f4-grh7-6pcq | CVE-2026-48069 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-f596-whhp-79r4 | CVE-2026-101915 | low | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:N/A:N | yes |
| GHSA-m9gg-hp2v-232j | CVE-2026-101916 | high | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:N | yes |
| GHSA-j965-2qgj-vjmq | low | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:N/A:N | no | |
| GHSA-3g43-6gmg-66jw | CVE-2026-44495 | high | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:L/A:L | yes |
| GHSA-3p68-rc4w-qgx5 | CVE-2025-62718 | medium | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:N | yes |
| GHSA-43fc-jf86-j433 | CVE-2026-25639 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-5c9x-8gcm-mpgx | CVE-2026-42034 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| GHSA-62hf-57xw-28j9 | CVE-2026-42039 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-6chq-wfr3-2hj9 | CVE-2026-42035 | high | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:N | yes |
| GHSA-7q8q-rj6j-mhjq | CVE-2026-67319 | medium | yes | |
| GHSA-898c-q2cr-xwhg | CVE-2026-44490 | medium | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L | yes |
| GHSA-fvcv-3m26-pcqx | CVE-2026-40175 | medium | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:N | yes |
| GHSA-hfxv-24rg-xrqf | CVE-2026-44496 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-j5f8-grm9-p9fc | CVE-2026-44486 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N | yes |
| GHSA-jr5f-v2jv-69x6 | CVE-2025-27152 | high | yes | |
| GHSA-m7pr-hjqh-92cm | CVE-2026-42038 | medium | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:N/A:N | yes |
| GHSA-mmx7-hfxf-jppx | CVE-2026-67316 | medium | yes | |
| GHSA-p92q-9vqr-4j8v | CVE-2026-44487 | high | yes | |
| GHSA-pf86-5x62-jrwf | CVE-2026-42033 | high | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:N | yes |
| GHSA-pjwm-pj3p-43mv | CVE-2026-44492 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:N/A:N | yes |
| GHSA-pmwg-cvhr-8vh7 | CVE-2026-42043 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N | yes |
| GHSA-vf2m-468p-8v99 | CVE-2026-42036 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| GHSA-w9j2-pvgh-6h63 | CVE-2026-42041 | medium | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:L/A:N | yes |
| GHSA-wf5p-g6vw-rhxx | CVE-2023-45857 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N | yes |
| GHSA-xhjh-pmcv-23jw | CVE-2026-42040 | low | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N | yes |
| GHSA-xx6v-rp6x-q39c | CVE-2026-42042 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:N | yes |
| GHSA-2pr8-phx7-x9h3 | CVE-2026-44294 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| GHSA-66ff-xgx4-vchm | CVE-2026-44293 | high | yes | |
| GHSA-685m-2w69-288q | CVE-2026-44289 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-75px-5xx7-5xc7 | CVE-2026-44291 | high | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H | yes |
| GHSA-f38q-mgvj-vph7 | CVE-2026-54269 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| GHSA-fx83-v9x8-x52w | CVE-2026-44292 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N | yes |
| GHSA-h755-8qp9-cq85 | CVE-2023-36665 | critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H | yes |
| GHSA-jggg-4jg4-v7c6 | CVE-2026-45740 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| GHSA-jvwf-75h9-cwgg | CVE-2026-44290 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-q6x5-8v7m-xcrf | CVE-2026-44288 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N | yes |
| GHSA-wcpc-wj8m-hjx6 | CVE-2026-48712 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-xq3m-2v4x-88gg | CVE-2026-41242 | critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H | yes |
| GHSA-w5hq-g745-h8pq | CVE-2026-41907 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:N | yes |
| 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 303 packages
| Packages resolved | 303 |
|---|---|
| Deprecated | 9 |
| Stale | 115 |
| No linked repository | 2 |
| 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 →
list-secrets List ARA Secrets ~58
List all supported secrets in the account — both dynamic and rotated (databases and services like AWS, GCP, Azure, Kubernetes, GitHub).
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | – | Optional Akeyless folder path to filter results (default /) |
No output schema declared.
No examples provided.
list-sub-tools List Service Sub-Tools ~195
OPTIONAL helper for service secrets only (NOT for database secrets — query-db does not need this). Lists the sub-tools (and their parameters) that the service behind the given secret exposes. This call is never required: service-execute already accepts natural language or CLI-style payloads. Use it only when you want to discover the exact sub-tool name and parameters before calling service-execute, e.g. 1) list-secrets, 2) (optional) list-sub-tools with the chosen service secret, 3) service-execute with a payload that invokes the chosen sub-tool with its required parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| agent-id | string | – | Agent identifier for auditing and session-scoped credential caching. |
| secret-name | string | yes | Full path of the Akeyless secret. Must be a service secret (e.g. AWS, GCP, Azure, Kubernetes, GitHub, custom MCP) — not a database secret. |
No output schema declared.
No examples provided.
query-db Query Database ~210
Execute a query against a database using Akeyless secret credentials (dynamic or rotated). Supports MySQL, PostgreSQL, MSSQL, Oracle, Snowflake, HanaDB, Redshift, MongoDB, Redis, and Cassandra. Returns the query results as a JSON array of objects. IMPORTANT: Always ask the user for the secret name if it was not provided in the conversation, you can use the list-secrets tool to get the list of available secrets.
| Name | Type | Req | Description |
|---|---|---|---|
| agent-id | string | – | Agent identifier for auditing purposes. |
| original-prompt | string | – | The user's original natural-language request before the agent translated it into a query. |
| original-user | string | – | The human end-user behind the agent (for auditing). |
| payload | string | yes | The query or command to execute (e.g. SELECT * FROM users LIMIT 10). |
| secret-name | string | yes | Full path of the Akeyless secret — dynamic or rotated (e.g. /MyFolder/my-mysql-ds). |
No output schema declared.
No examples provided.
service-execute Execute Service Action ~293
Execute an action against a service (AWS, GCP, Azure, Kubernetes, or GitHub) using Akeyless secret credentials (dynamic or rotated). Accepts natural language or CLI-style payloads (e.g. 'list all S3 buckets', 'kubectl get pods -n default', 'list open PRs'). Returns the results as JSON. Credentials are never exposed. IMPORTANT: Always ask the user for the secret name if it was not provided. Use the list-secrets tool to discover available secrets.
| Name | Type | Req | Description |
|---|---|---|---|
| agent-id | string | – | Agent identifier for auditing purposes. |
| auth-code | string | – | OAuth authorization code returned after the user authorizes in the browser. Only required when the previous call returned an authorization URL. |
| original-prompt | string | – | The user's original natural-language request before the agent translated it into an action. |
| original-user | string | – | The human end-user behind the agent (for auditing). |
| payload | string | yes | The action to execute. Can be natural language (e.g. 'list all S3 buckets') or CLI-style (e.g. 'aws s3 ls'). |
| secret-name | string | yes | Full path of the Akeyless secret — dynamic or rotated (e.g. /MyFolder/my-aws-ds). |
| state | string | – | OAuth state parameter returned with the authorization URL. Must be passed back together with auth-code. |
No output schema declared.
No examples provided.
How do I install the Akeyless Agentic Runtime Authority MCP server?
Akeyless Agentic Runtime Authority runs locally as an npm package, launched with npx -y @akeyless-community/devin-connector. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @akeyless-community/devin-connector
claude mcp add akeyless-community-akeyless-rta -- npx -y @akeyless-community/devin-connector
What is the Akeyless Agentic Runtime Authority MCP server?
Akeyless Agentic Runtime Authority is an MCP server listed in the public MCP registry as io.github.akeyless-community/akeyless-rta. Secretless database and cloud access via Akeyless RTA. Credentials never enter the model. This page covers its npm package (@akeyless-community/devin-connector).
What tools does the Akeyless Agentic Runtime Authority MCP server expose?
Akeyless Agentic Runtime Authority exposes 4 tools: query-db, service-execute, list-sub-tools, list-secrets. Their descriptions and schemas cost roughly 756 tokens of context every time the server is loaded.
Is the Akeyless Agentic Runtime Authority MCP server still maintained?
Akeyless Agentic Runtime Authority 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 Akeyless Agentic Runtime Authority MCP server under?
Akeyless Agentic Runtime Authority declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.