Connections
NPM · CONNECTIONS-MCP
AWS, GitHub and connected services from your agent, no keys to paste, plus local shell and browser.
Available components
Last scanned (23 hours ago)
Scores higher than 38% of npm servers
Category Cloud Infrastructure
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 Security100
- 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
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency6
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Licence could not be checked: the licence is shipped as a file inside the package, not declared as a standard (SPDX) licence identifier, so we cannot tell whether it is OSI-approved.Unverified
- Actively maintained (last published 3 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability68
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1145 tokens (~572/item across 2 items; 2 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 Management57
- Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage86
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 59% 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
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
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.
- 16 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Oct 26 +35
- Injection markers: unverified → pass ▲ security
- MCP protocol: unverified → fail ▼ functional
- Tool coverage: 53% → 59% ▲ functional
- Schema quality: 1186 → 572 ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- Stability: unverified → 0.50 ▲ functional
- Schema quality: unverified → 100 ▲ functional
- Schema quality: excellent → good functional
- Package version: 2.191.4 → 2.240.0 functional
- 13 Oct 26 0
- Package version: 2.191.4 → 2.240.0 functional
- 12 Oct 26 −28
- Tool safety: pass → unverified ▼ security
- Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
- Capabilities: fail → unverified ▼ functional
- License: fail → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Licence: UNLICENSED functional
- Package version: 2.191.4 → 2.240.0 functional
- Package version: 2.191.4 → 2.231.0 functional
- 30 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 29 Sept 26 44
First indexed and scored.
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 16 Oct 2026 · Analysed npm/connections-mcp@2.240.0
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 0 packages
| Packages resolved | 0 |
|---|---|
| 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 →
connections_execute Run a local tool or a catalog endpoint ~424
Run something found with connections_search_catalog. (1) A LOCAL tool on this machine: { local:true, tool_name, params }; runs here, no sign-in. (2) A catalog API ENDPOINT: { endpoint_id } (or service+tool_name); runs as this workspace's company with the vaulted credential injected server-side (value-blind; auto browser sign-in if needed, no key to paste). Target a connected account with `instance`.
| Name | Type | Req | Description |
|---|---|---|---|
| company | string | – | Run this call as another company you belong to (companyId, projectId or exact name from connections_list_companies), e.g. email_action inbox.threads for its inbox. Refused if you are not a member. Om… |
| endpoint_id | string | – | – |
| files | object | – | Catalog endpoints only: { "<params field>": "<file path>" }; this machine reads each file into that params field as base64 (dotted, e.g. "data_base64"), so the bytes never pass through you. Never bas… |
| instance | string | – | – |
| jmespath | string | – | Optional JMESPath applied to the JSON answer, e.g. body.items[*].id (grammar: connections_briefing). |
| local | boolean | – | true → run tool_name as a LOCAL tool instead of a catalog endpoint. |
| params | object | – | – |
| params_file | string | – | A JSON object file (relative to this workspace or absolute) read into params on this machine. Give params OR params_file, never both. |
| project | string | – | Which COMPANY/workspace THIS call runs against: a company id, project id or ref (Studio's ?project= on a catalog call; a one-call pin on a local tool, refused if you are not a member, and the reply n… |
| service | string | – | – |
| tool_name | string | – | – |
| workflow | – | – | – |
No output schema declared.
No examples provided.
connections_search_catalog Search your local tools and the Connections catalog ~265
Find something to run: your LOCAL tools on this machine (browser/shell/git/deploy/ssh/architect/…) and every API endpoint this workspace's company can call (first-party + connected third-party). A local tool's exact name → that one tool, catalog not searched. An endpoint's or Script Vault instrument's exact tool_name → that row first, ahead of every fuzzy hit (an instrument with its full description). Auto browser sign-in if needed (no key to paste).
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Your CONTEXT budget - bounds the whole response, not just the endpoint list (default 8, max 25). |
| query | string | – | What to find; blank → your full local-tool inventory. |
| service | string | – | – |
| use_case | string | – | What you are trying to get done, in a sentence (e.g. 'deploy the pay lambda and check its logs'). Sharpens the local-tool ranking; alone it is the query. The top local hit lists the tools usually run… |
| verbose | boolean | – | false (default): endpoint hits list param names only, local tools and Script Vault instruments a one-line summary. true: each hit's full parameter schema and description. |
No output schema declared.
No examples provided.
How do I install the Connections MCP server?
Connections runs locally as an npm package, launched with npx -y connections-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 · connections-mcp
claude mcp add lunarwerx-connections -- npx -y connections-mcp
What is the Connections MCP server?
Connections is an MCP server listed in the public MCP registry as io.github.Lunarwerx/connections. AWS, GitHub and connected services from your agent, no keys to paste, plus local shell and browser. This page covers its npm package (connections-mcp).
Is the Connections MCP server safe to use?
Connections scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 16 October 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 Connections MCP server expose?
Connections exposes 2 tools: connections_search_catalog, connections_execute. Their descriptions and schemas cost roughly 689 tokens of context every time the server is loaded.
Is the Connections MCP server still maintained?
Connections is still listed as active in the MCP registry. We last reached this channel on 16 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.