Calypso Multimodal RAG MCP
NPM · @CALYPSOHQ/MULTIMODAL-RAG-MCP-SERVER · SCANNED AUG 3
Calypso multimodal RAG for grounded answers from docs, images, charts, and knowledge.
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 →
Supply Chain Security87
- No malware found by supply-chain analysis.Pass
- Only part of the dependency tree could be resolved (124 of 125), so this covers what we could see, not the whole tree.Partial
- No install/post-install scripts declared.Pass
- Only part of the dependency tree could be resolved (124 of 125), so this covers what we could see, not the whole tree. 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 54 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability75
- 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 1712 tokens (~171/item across 10 items; 5 tools + 5 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 Management27
- Stability observed for 8 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
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.
npm · @calypsohq/multimodal-rag-mcp-server
claude mcp add calypso-so-multimodal-rag-mcp-server -- npx -y @calypsohq/multimodal-rag-mcp-server
codex mcp add calypso-so-multimodal-rag-mcp-server -- npx -y @calypsohq/multimodal-rag-mcp-server
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"calypso-so-multimodal-rag-mcp-server": {
"type": "local",
"command": [
"npx",
"-y",
"@calypsohq/multimodal-rag-mcp-server"
],
"enabled": true
}
}
} openclaw mcp add calypso-so-multimodal-rag-mcp-server --command npx --arg -y --arg @calypsohq/multimodal-rag-mcp-server
mcp_servers:
calypso-so-multimodal-rag-mcp-server:
command: "npx"
args: ["-y", "@calypsohq/multimodal-rag-mcp-server"] {
"mcpServers": {
"calypso-so-multimodal-rag-mcp-server": {
"command": "npx",
"args": [
"-y",
"@calypsohq/multimodal-rag-mcp-server"
]
}
}
} 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 Aug 26 +4
- Stability: unverified → 0.27 ▲ functional
- 2 Aug 26 +40
- Provenance: unverified → fail ▼ security
- Install scripts: unverified → pass ▲ security
- Known CVEs: unverified → partial ▲ security
- Malware scan: unverified → pass ▲ security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Security disclosure: fail → unverified ▼ functional
- License: unverified → pass ▲ functional
- Dependency health: unverified → partial ▲ functional
- Maintenance: unverified → pass ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Schema quality: unverified → good ▲ functional
- Licence: MIT functional
- 1 Aug 26 +20
- Tool coverage: unverified → 100 ▲ functional
- Schema quality: unverified → 100 ▲ functional
- 31 Jul 26 −19
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 30 Jul 26 −27
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- 27 Jul 26 51
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 3 Aug 2026 · Analysed npm/@calypsohq/[email protected]
Provenance none
Ecosystem: npm · Outcome: none
Dependencies 124 packages
124 packages in the resolved dependency tree · 122 deprecated · 37 stale.
The dependency tree was only partially resolved, so these counts may be incomplete.
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.
calypso-list-knowledge-buckets ~116
[CALYPSO LIST KNOWLEDGE BUCKETS] Lists knowledge buckets for the team tied to the configured Calypso API key. Use this before uploads when you need bucket ids, slugs, names, member counts, or bucket-store readiness. This complements RAG model discovery: model discovery shows which buckets are bound to each agent variant, while this tool lists all buckets for the API key team.
| Name | Type | Req | Description |
|---|---|---|---|
| includeArchived | boolean | — | If true, include archived buckets. Defaults to false. |
No output schema declared.
No examples provided.
calypso-rag-agent ~352
[CALYPSO RAG AGENT] Sends each prompt directly to the Calypso RAG agent using the full conversation context. Use this when you want Calypso knowledge retrieval and grounded answers from the RAG backend. Typical requests: - "Summarize the key points from our onboarding documentation" - "What does the knowledge base say about campaign approval rules?" - "Compare the documented indexing flow with the retrieval flow" - "Answer using the uploaded file ids: [\"file_123\"]" Responses API behavior: - First turns start a named Calypso conversation via `/v1/responses`. - Follow-up turns chain with `previous_response_id` so the backend owns conversation state. - When `fileIds` are provided, the MCP uses `rag_policy` retrieval semantics instead of inline attachment stuffing. MCP session behavior: - This tool maintains a stable conversation id in the background for multi-turn retrieval context. - Use `/new` to start a fresh conversation and clear the current context window. Quick commands (examples): - "Summarize the latest indexed knowledge about WhatsApp templates" - "Find the source of truth for campaign approval behavior" - "Start a new topic" (or use `/new`) Available RAG models: calypso-rag-agent.
| Name | Type | Req | Description |
|---|---|---|---|
| fileIds | array | — | Optional uploaded agent-store `file_id` values to attach with `rag_policy` retrieval semantics. |
| model | string | — | Optional RAG model variant. Defaults to `calypso-rag-agent`. Available models: calypso-rag-agent. |
| prompt | string | yes | Your request. Include context, constraints, and desired output. |
No output schema declared.
No examples provided.
calypso-upload-agent-file ~355
[CALYPSO UPLOAD AGENT FILE] Uploads a file through the agent-facing API, backed by one durable knowledge bucket. Use this when you want a compatible `file_id` that can be attached to `calypso-rag-agent`. The MCP sends `purpose=user_data`, targets the selected RAG agent with `target_model`, passes exactly one `bucket_id`, and can optionally wait until the file is RAG-ready before returning. For Claude, Smithery, browser, or hosted-agent uploads, pass `contentBase64`; use `filePath` only when this MCP process can read that exact local path. Bucket bindings by model: calypso-rag-agent: no active buckets configured.
| Name | Type | Req | Description |
|---|---|---|---|
| bucketId | string | — | Required when the selected model has multiple buckets. Auto-selected when the selected model has exactly one active bucket. |
| contentBase64 | string | — | Base64-encoded file content. Recommended for Claude, Smithery, browser, and remote-agent uploads because the MCP process receives the bytes directly. |
| filePath | string | — | Advanced local-only path. Use only when the Calypso MCP server is running on the same filesystem and can read this exact path; hosted attachment paths such as /mnt/user-data/uploads usually require c… |
| filename | string | yes | Display filename for the uploaded file. |
| mimeType | string | yes | Content type for the uploaded file. |
| targetModel | string | — | Optional RAG agent id. Defaults to `calypso-rag-agent`. Available models: calypso-rag-agent. |
| waitForReady | boolean | — | If true, wait until the uploaded file is RAG-ready before returning. |
No output schema declared.
No examples provided.
calypso-upload-knowledge-file ~428
[CALYPSO UPLOAD KNOWLEDGE FILE] Uploads a file into the durable bucket-backed knowledge store and indexing pipeline. Use this when you want a file indexed into the broader knowledge corpus instead of attached directly to a single RAG chat turn. This tool returns knowledge-file and task metadata. A bucket destination is required: pass bucketIds, bucketSlugs, or bucket. For Claude, Smithery, browser, or hosted-agent uploads, pass `contentBase64`; use `filePath` only when this MCP process can read that exact local path.
| Name | Type | Req | Description |
|---|---|---|---|
| bucket | string | — | Convenience single bucket slug for this upload. Required unless bucketIds or bucketSlugs is provided. |
| bucketIds | array | — | Existing knowledge bucket ids to assign this upload to. Required unless bucketSlugs or bucket is provided. |
| bucketSlugs | array | — | Knowledge bucket slugs to assign this upload to. Required unless bucketIds or bucket is provided. |
| contentBase64 | string | — | Base64-encoded file content. Recommended for Claude, Smithery, browser, and remote-agent uploads because the MCP process receives the bytes directly. |
| createMissingBuckets | boolean | — | If true, create missing bucket slugs before assignment. |
| filePath | string | — | Advanced local-only path. Use only when the Calypso MCP server is running on the same filesystem and can read this exact path; hosted attachment paths such as /mnt/user-data/uploads usually require c… |
| filename | string | yes | Display filename for the uploaded knowledge file. |
| idempotencyKey | string | — | Optional idempotency key for durable upload retries. |
| metadata | object | — | Optional metadata object serialized onto the upload request. |
| mimeType | string | yes | Content type for the uploaded knowledge file. |
| tags | array | — | Optional tags for knowledge-store organization. |
| title | string | — | Optional human-readable title stored with the knowledge file. |
| waitForIndexing | boolean | — | If true, wait until indexing reaches a terminal ready state before returning. |
No output schema declared.
No examples provided.
calypso-upload-knowledge-files-batch ~333
[CALYPSO UPLOAD KNOWLEDGE FILES BATCH] Uploads 1 to 100 files into the durable knowledge store and indexing queue in one request. Use this for bulk corpus ingestion. Shared bucket fields apply to every item unless an item provides its own bucket fields. The tool returns batch-level status and, when requested, polls until the batch reaches active, partially_active, partially_failed, failed, or timeout. A shared bucket destination is required unless every item provides its own bucket destination. For Claude, Smithery, browser, or hosted-agent uploads, pass `contentBase64` per item; use `filePath` only for files local to this MCP process.
| Name | Type | Req | Description |
|---|---|---|---|
| batchIdempotencyKey | string | yes | Required idempotency key used to derive the durable batch id. |
| bucket | string | — | Convenience single bucket slug applied to all items by default. Required unless every item has a bucket destination. |
| bucketIds | array | — | Existing bucket ids applied to all items by default. Required unless every item has a bucket destination. |
| bucketSlugs | array | — | Bucket slugs applied to all items by default. Required unless every item has a bucket destination. |
| createMissingBuckets | boolean | — | If true, create missing shared bucket slugs before assignment. |
| dryRun | boolean | — | If true, validate the batch request without storing files. |
| items | array | yes | Knowledge files to upload in this batch. |
| waitForBatchReady | boolean | — | If true, poll batch status with include_items=true until terminal or timeout. |
No output schema declared.
No examples provided.