Casama
NPM · @CASAMA/MCP · 2 COMPONENTS
Search Casama's docs and API reference, no sign-in. Optional: drive your Casama AI bots.
Available components
Last scanned (12 hours ago)
Scores higher than 37% of npm servers
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 93 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 1 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability63
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 1390 tokens (~63/item across 22 items; 22 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management3
- Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage76
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 28% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "ask_bot" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 22 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.
- 20 Nov 26 65
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 21 Nov 2026 · Analysed npm/@casama/mcp@0.2.1
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 93 packages
| Packages resolved | 93 |
|---|---|
| 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 →
ask_bot Ask a bot ~86
Send a message to a Casama bot and wait for its reply. The bot can use its own computer and tools; risky actions may wait for approval (see list_approvals). Pass conversation_id to continue a thread.
| Name | Type | Req | Description |
|---|---|---|---|
| bot | string | yes | Bot name or id |
| conversation_id | string | – | – |
| message | string | yes | – |
| workspace | string | – | – |
No output schema declared.
No examples provided.
check_domain Check a domain's DNS now ~48
Check a domain's DNS and certificate now instead of waiting for the next check (admins; at most once every 10 seconds).
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | – |
| workspace | string | – | – |
No output schema declared.
No examples provided.
check_plugin Check a plugin ~73
Check an Agent Plugins 1.0 folder (plugin.json, mcp.json, skills/) on this computer the way Casama checks it at install: errors (refused), warnings (skipped or ignored) and tips.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | The plugin folder, absolute or relative to where the server runs |
No output schema declared.
No examples provided.
connect_domain Connect a domain ~80
Connect a domain the workspace already owns (bakery.com, www.bakery.com or shop.bakery.com), optionally showing a published site. Answers the DNS records to add at the domain's DNS company (admins).
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | – |
| page_id | string | – | A published site's page id |
| workspace | string | – | – |
No output schema declared.
No examples provided.
decide_approval Approve or deny ~44
Approve or deny a pending action. The bot continues (or skips the step) right away.
| Name | Type | Req | Description |
|---|---|---|---|
| approval_id | string | yes | – |
| decision | string | yes | – |
No output schema declared.
No examples provided.
gallery_search Search the Casama gallery ~112
Search the Casama gallery (gallery.casama.ai) for ready-made skills, apps, routines, bots, plugins, starter sets and looks before writing a new one. Returns the best matches with what each can access, what it needs and its page. Add one in Casama from its page, or start from it with `casama init --from-gallery bot/<id>` or `plugin/<id>`.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| query | string | yes | – |
| types | array | – | – |
No output schema declared.
No examples provided.
get_api_operation Look up the Casama API ~87
Find operations in the Casama HTTP API (OpenAPI 3.1) and show their parameters, request body and responses as types. Query by operationId ("createBot"), "METHOD /path" ("POST /v1/conversations/{id}/messages", concrete ids work too) or keywords ("cancel run").
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| query | string | yes | – |
No output schema declared.
No examples provided.
get_domain Get a domain ~49
A domain's hosts and states, the DNS records to add with what DNS shows now, renewal details and history.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | Domain id or name |
| workspace | string | – | – |
No output schema declared.
No examples provided.
get_run Get a run ~34
A run's status, cost and its recent events (tool calls, outputs, errors).
| Name | Type | Req | Description |
|---|---|---|---|
| run_id | string | yes | – |
No output schema declared.
No examples provided.
install_pack Install a pack ~111
Install a pack in a workspace, pinned to the commit preview_pack showed. Show the person the preview first. Secrets aren't taken here: the person adds them in the app. Packs that aren't reviewed start their routines switched off; the workspace's gallery rules apply.
| Name | Type | Req | Description |
|---|---|---|---|
| commit | string | – | – |
| gallery_id | string | – | – |
| inputs | object | – | Answers to its questions |
| skip | array | – | Items to leave out |
| url | string | – | – |
| workspace | string | – | – |
No output schema declared.
No examples provided.
list_approvals List approvals ~27
Actions waiting for a person's approval in a workspace.
| Name | Type | Req | Description |
|---|---|---|---|
| workspace | string | – | – |
No output schema declared.
No examples provided.
list_bots List bots ~38
Bots in a workspace (default: your first workspace), with their current status.
| Name | Type | Req | Description |
|---|---|---|---|
| workspace | string | – | Workspace slug, name or id |
No output schema declared.
No examples provided.
list_doc_pages List docs pages ~22
Every page on docs.casama.ai with its title and address.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_domains List domains ~44
Connected and bought domains in a workspace: the site each shows and its state (live, waiting_dns, waiting_cert, paused, needs_attention).
| Name | Type | Req | Description |
|---|---|---|---|
| workspace | string | – | – |
No output schema declared.
No examples provided.
list_packs List installed packs ~35
Packs installed in a workspace: plugins that brought bots, skills, routines, apps and looks.
| Name | Type | Req | Description |
|---|---|---|---|
| workspace | string | – | – |
No output schema declared.
No examples provided.
list_sites List sites ~34
Pages published on the web at their own address in a workspace, with their hosts and states.
| Name | Type | Req | Description |
|---|---|---|---|
| workspace | string | – | – |
No output schema declared.
No examples provided.
list_workspaces List workspaces ~21
Casama workspaces you belong to, with your role.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
preview_pack Preview a pack ~92
What a pack from a GitHub link (or a reviewed pack from the directory, by id) would add: bots, skills, routines, apps, looks, tools, the questions it asks, what it can reach and the commit to install.
| Name | Type | Req | Description |
|---|---|---|---|
| gallery_id | string | – | A pack from the plugin directory |
| url | string | – | A GitHub repository or folder |
| workspace | string | – | – |
No output schema declared.
No examples provided.
react_to_message React to a message ~140
React to a message in a conversation with one emoji (D-331), or take your reaction back. Without message_id it reacts to the bot's latest reply. One reaction per person per message: another emoji replaces yours. The bot sees it the next time it works in that chat; a 👍 or 👎 tells it whether the reply worked.
| Name | Type | Req | Description |
|---|---|---|---|
| bot | string | yes | Bot name or id |
| conversation_id | string | yes | – |
| emoji | string | yes | Exactly one emoji, e.g. 👍 |
| message_id | string | – | – |
| remove | boolean | – | Take your reaction back instead |
| workspace | string | – | – |
No output schema declared.
No examples provided.
read_doc Read a docs page ~76
One docs page as markdown, by path or address: "/develop/plugins", "develop/api.md" or "https://docs.casama.ai/guide/skills". Pass section to get one ## section only.
| Name | Type | Req | Description |
|---|---|---|---|
| page | string | yes | – |
| section | string | – | A ## heading on the page, e.g. "Secrets" |
No output schema declared.
No examples provided.
search_docs Search the Casama docs ~77
Keyword search over docs.casama.ai (guides, self-hosting, the API, CLI, SDKs, plugins, webhooks, A2A, bot templates, contributing). Returns the best-matching sections with their address; read a whole page with read_doc.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| query | string | yes | – |
No output schema declared.
No examples provided.
search_domains Search domains to buy ~60
Domain names for a few words or a name, with availability, the first year's price and the renewal price (before tax). Only a person can buy one, in the Casama app.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | – |
| workspace | string | – | – |
No output schema declared.
No examples provided.
How do I install the Casama MCP server?
Casama runs locally as an npm package, launched with npx -y @casama/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 · @casama/mcp
claude mcp add stackwares-casama -- npx -y @casama/mcp
What is the Casama MCP server?
Casama is an MCP server listed in the public MCP registry as io.github.stackwares/casama. Search Casama's docs and API reference, no sign-in. Optional: drive your Casama AI bots. This page covers its npm package (@casama/mcp).
Is the Casama MCP server safe to use?
Casama scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 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 Casama MCP server expose?
Casama exposes 22 tools: search_docs, read_doc, list_doc_pages, get_api_operation, check_plugin, and 17 more. Their descriptions and schemas cost roughly 1,390 tokens of context every time the server is loaded.
Is the Casama MCP server still maintained?
Casama is still listed as active in the MCP registry. We last reached this channel on 21 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 Casama MCP server under?
Casama 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 Casama MCP server?
VerifyMCP ran 16 checks on Casama, 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.