ContinueWith
NPM · @CONTINUEWITH/MCP · SCANNED SEP 22
Install the ContinueWith AI handoff widget from coding agents (Cursor, Claude Code, Codex).
Available components
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
- 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- 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 (MIT).Pass
- Actively maintained (last published 77 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability72
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 797 tokens (~61/item across 13 items; 13 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 Coverage94
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 82% 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 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 13 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
How do I install the ContinueWith MCP server?
ContinueWith runs locally as an npm package, launched with npx -y @continuewith/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 · @continuewith/mcp
claude mcp add continuewith-ai-continuewith -- npx -y @continuewith/mcp
{
"mcpServers": {
"continuewith-ai-continuewith": {
"command": "npx",
"args": [
"-y",
"@continuewith/mcp"
]
}
}
} {
"servers": {
"continuewith-ai-continuewith": {
"command": "npx",
"args": [
"-y",
"@continuewith/mcp"
]
}
}
} codex mcp add continuewith-ai-continuewith -- npx -y @continuewith/mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"continuewith-ai-continuewith": {
"type": "local",
"command": [
"npx",
"-y",
"@continuewith/mcp"
],
"enabled": true
}
}
} openclaw mcp add continuewith-ai-continuewith --command npx --arg -y --arg @continuewith/mcp
mcp_servers:
continuewith-ai-continuewith:
command: "npx"
args: ["-y", "@continuewith/mcp"] {
"McpServers": {
"continuewith-ai-continuewith": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@continuewith/mcp"
]
}
}
} assistant mcp add continuewith-ai-continuewith -t stdio -c npx -a -y @continuewith/mcp
{
"mcpServers": {
"continuewith-ai-continuewith": {
"command": "npx",
"args": [
"-y",
"@continuewith/mcp"
]
}
}
} 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.
- 22 Sept 26 +1
- Stability: 0.97 → pass security
- 20 Sept 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.
- 18 Sept 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.
- 16 Sept 26 −3
- Stability: pass → 0.80 functional
- 15 Sept 26 +1
- Stability: 0.97 → pass security
- 13 Sept 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.
- 11 Sept 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.
- 9 Sept 26 −3
- Security disclosure: unverified → fail ▼ functional
- 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 22 Sept 2026 · Analysed npm/@continuewith/mcp@0.1.4
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 96 packages
| Packages resolved | 96 |
|---|---|
| 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 →
get_agent_install_rule ~26
Return the default rule for coding agents to auto-install ContinueWith on marketing pages.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_continuewith_docs ~20
Return ContinueWith documentation URLs for agents and installers.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_install_snippet ~142
Return the ContinueWith widget install snippet for html, nextjs, or astro.
| Name | Type | Req | Description |
|---|---|---|---|
| background | string | – | Theme panel background |
| borderColor | string | – | Theme border color |
| framework | string | – | Target stack |
| layout | string | – | Widget layout inside the panel |
| mode | string | – | Widget display mode. Defaults to floating. |
| primaryColor | string | – | Theme primary color |
| siteKey | string | – | Public site key. Defaults to cw_demo_public_key. |
| target | string | – | CSS selector for inline mode, e.g. #continuewith-widget |
| textColor | string | – | Theme text color |
No output schema declared.
No examples provided.
install_continuewith_widget ~139
Run `npx continuewith add` in a project directory to patch the layout or HTML file.
| Name | Type | Req | Description |
|---|---|---|---|
| background | string | – | Theme background |
| borderColor | string | – | Theme border color |
| framework | string | – | Optional framework override |
| layout | string | – | Widget layout |
| mode | string | – | Widget display mode |
| primaryColor | string | – | Theme primary color |
| projectPath | string | yes | Absolute or relative path to the project root |
| siteKey | string | – | Optional public site key |
| target | string | – | Inline mount selector |
| textColor | string | – | Theme text color |
No output schema declared.
No examples provided.
loop_create_submission ~39
Start a submission attempt for a directory. Returns attempt id for blocker reporting.
| Name | Type | Req | Description |
|---|---|---|---|
| directoryId | string | yes | – |
| notes | string | – | – |
No output schema declared.
No examples provided.
loop_get_project_profile ~39
Get the active Distribution Loop project profile and optional completeness for a directory.
| Name | Type | Req | Description |
|---|---|---|---|
| directoryId | string | – | Optional directory id for directory-specific completeness |
No output schema declared.
No examples provided.
loop_get_submission_assets ~43
Get generated submission copy (tagline, descriptions, URLs) for a directory by id.
| Name | Type | Req | Description |
|---|---|---|---|
| directoryId | string | yes | Directory UUID from loop_list_directories |
No output schema declared.
No examples provided.
loop_get_summary ~23
Dashboard summary for Distribution Loop: counts, open blockers, API endpoints.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
loop_list_blockers ~22
List open human-in-the-loop blockers waiting for operator input.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
loop_list_directories ~89
List AI Distribution Loop directories with fit scores, submission URLs, and status filters.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max rows to show (default 15) |
| priority | string | – | Filter by priority: low, medium, high |
| q | string | – | Search name, domain, or tags |
| status | string | – | Filter by status, e.g. selected, not_started |
No output schema declared.
No examples provided.
loop_report_blocker ~62
Pause a submission and ask the human operator for help (login, captcha, missing field, payment, etc.).
| Name | Type | Req | Description |
|---|---|---|---|
| fieldKey | string | – | – |
| message | string | yes | – |
| submissionId | string | yes | – |
| type | string | yes | – |
No output schema declared.
No examples provided.
loop_resolve_blocker ~48
Mark a human blocker as resolved so the agent can resume the submission attempt.
| Name | Type | Req | Description |
|---|---|---|---|
| resolutionPayload | object | – | Field values supplied by the human |
| submissionId | string | yes | – |
No output schema declared.
No examples provided.
search_ready_directory ~105
Search the AI Ready Index — agent-ready websites with AI readiness scores, categories, and ContinueWith handoff signals.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Filter by category, e.g. SaaS |
| continueWith | boolean | – | Only sites with ContinueWith widget installed |
| limit | integer | – | Max results to return (default 10) |
| partner | boolean | – | Only featured ContinueWith partner listings |
| q | string | – | Search name, description, or tags |
No output schema declared.
No examples provided.
What is the ContinueWith MCP server?
ContinueWith is an MCP server listed in the public MCP registry as io.github.continuewith-ai/continuewith. Install the ContinueWith AI handoff widget from coding agents (Cursor, Claude Code, Codex). This page covers its npm package (@continuewith/mcp).
Is the ContinueWith MCP server safe to use?
ContinueWith scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 September 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 ContinueWith MCP server expose?
ContinueWith exposes 13 tools: get_agent_install_rule, get_install_snippet, get_continuewith_docs, install_continuewith_widget, search_ready_directory, and 8 more. Their descriptions and schemas cost roughly 797 tokens of context every time the server is loaded.
Is the ContinueWith MCP server still maintained?
ContinueWith is still listed as active in the MCP registry. We last reached this channel on 22 September 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 ContinueWith MCP server under?
ContinueWith declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.