TalkJS MCP server
com.talkjs/talkjstalkjs.comstreamable-httpv0.1.2Scanned
Let your AI assistant configure and manage TalkJS chat in your app.
8 tools: 3 can delete or cancel things, 1 change things and 4 only read.
- Reads private data · 2
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
Anlyon alternative
4 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →Its sign-in does not let Anlyon set up an OAuth client on its own, so there is no link to it here.
What the TalkJS MCP server can do
The TalkJS MCP server is published by talkjs.com, a domain the MCP Registry verified. It has 8 tools. It can delete or cancel things (3 tools: delete_secret_key, update_secret_key and update_settings) and create or change data (1 tool: create_secret_key). 4 tools only read.
2 tools read private data (get_secret_key and list_secret_keys).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 18, 2026, version 0.1.2.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
8 tools
Deletes or cancels 3Claude Code: deny
delete_secret_keyPermanently delete an inactive secret key that is not selected for webhooks, from the connected test app.No findings
Why it is in this group
- The name "delete_secret_key" says "delete": a word for removing or ending something.
- The description says "Permanently delete".
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Permanently delete an inactive secret key that is not selected for webhooks, from the connected test app. Deactivate it first; select a replacement if it is the current webhook key.
Annotations the server declares
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: false
update_secret_keyActivate/deactivate a test app secret key or select it for webhooks.No findings
Why it is in this group
- The name "update_secret_key" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Activate/deactivate a test app secret key or select it for webhooks. Supply active and/or usedForWebhooks as booleans. Select an active replacement before unselecting or deactivating the current webhook key. Returns metadata only.
Annotations the server declares
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: false
update_settingsUpdate the connected TalkJS test app's settings.No findings
Why it is in this group
- The name "update_settings" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Update the connected TalkJS test app's settings. Supply one or more fields. Custom fields merge; a null entry deletes that field, and custom: null clears all custom fields. Requiring authentication needs backend-generated user tokens; making it optional permits impersonation.
Annotations the server declares
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: false
Changes things 1Claude Code: ask
create_secret_keyCreate a new active secret key for the connected test app and return its ID and metadata only.No findings
Why it is in this group
- The name "create_secret_key" says "create": a word for a change.
Description, as the server wrote it Create a new active secret key for the connected test app and return its ID and metadata only. Never returns the secret value. Ask the user to view it in the TalkJS dashboard or manually run `talkjs secret-keys get <id>` in their terminal. Creates a new key on every call; at most 10 keys are allowed. Does not change webhook selection.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
Only reads 4Show 4 read-only tools
get_connection_statusCheck whether this request is connected to a TalkJS test app.No findings
Why it is in this group
- The name "get_connection_status" says "get": a word for reading.
Description, as the server wrote it Check whether this request is connected to a TalkJS test app. No login is required. When disconnected, returns concrete login instructions to show the user for their client.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_secret_keyGet a secret key's ID and metadata for the connected test app.Reads private dataNo findings
Why it is in this group
- The name "get_secret_key" says "get": a word for reading.
What it can reach
- private-dataThe name "get_secret_key" says "get" and "secret": it reads secrets.
- private-dataThe description's first sentence says "get" and "secret": it reads secrets.
Description, as the server wrote it Get a secret key's ID and metadata for the connected test app. Never returns the secret value. To view it, ask the user to open the key in the TalkJS dashboard or manually run `talkjs secret-keys get <id>` in their terminal.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_settingsRead basic settings for the connected TalkJS test app.No findings
Why it is in this group
- The name "get_settings" says "get": a word for reading.
Description, as the server wrote it Read basic settings for the connected TalkJS test app. Requires login and settings:read. If authentication is required, show the user the concrete steps for their client: Connect your TalkJS account using the steps for your client: - Codex CLI: type `/mcp login talkjs` in the active Codex session. - Claude Code: type `/mcp`, select the TalkJS server, and follow the authentication prompts. - ChatGPT web: use the Connect/Sign in prompt shown for the TalkJS tool. If no prompt appears, open the TalkJS plugin's connection settings and connect your account. - Claude web: open Customize > Connectors, find TalkJS, and click Connect. - Cursor: open Customize > MCP, select TalkJS, and follow the sign-in prompt. - Other MCP clients: open the TalkJS server's connection settings and choose Authenticate, Sign in, or Connect. `talkjs` in these commands is the configured MCP server name. Substitute the actual name if it was registered differently. Complete browser authorization, choose the TalkJS project's test app, then retry the requested operation. Terminal alternatives: run `codex mcp login talkjs` for Codex or `claude mcp login talkjs` for Claude Code. After terminal login, reconnect the MCP server in the active client if it still reports disconnected; start a new agent session if necessary.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
list_secret_keysList the connected test app's secret-key IDs, creation times, active status and webhook selection.Reads private dataNo findings
Why it is in this group
- The name "list_secret_keys" says "list": a word for reading.
What it can reach
- private-dataThe name "list_secret_keys" says "list" and "secret": it reads secrets.
- private-dataThe description's first sentence says "list" and "secret": it reads secrets.
Description, as the server wrote it List the connected test app's secret-key IDs, creation times, active status and webhook selection. Returns metadata only.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 18, 2026, 16:19 UTC, unchanged since Nov 18, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 4
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcp.talkjs.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://talkjs.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- no
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (3 destructive, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.talkjs.com/mcp: tools/list returned 8 tools to an anonymous client, including delete_secret_key (destructive), update_secret_key (destructive), update_settings (destructive), create_secret_key (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http talkjs https://mcp.talkjs.com/mcpclaude mcp add --transport http talkjs https://mcp.talkjs.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__talkjs__get_connection_status",
"mcp__talkjs__get_secret_key",
"mcp__talkjs__get_settings",
"mcp__talkjs__list_secret_keys"
],
"ask": [
"mcp__talkjs__create_secret_key"
],
"deny": [
"mcp__talkjs__delete_secret_key",
"mcp__talkjs__update_secret_key",
"mcp__talkjs__update_settings"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as talkjs. Review it before you use it.
Capability tags behind 2 rules
- mcp__talkjs__get_secret_key private-data
- mcp__talkjs__list_secret_keys private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.talkjs/talkjs/verify?hash=183f266b1859908e73609b672bf5e4c4ac73f21bf06c468907fef0f8021c159f" | jq -e '.changed == false'Pinned hash 183f266b1859, from Nov 18, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.talkjs/talkjs/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.talkjs/talkjs)Source: MCP Registry. Synced Nov 18, 2026, 14:17 UTC.
TalkJS MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the TalkJS MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 4 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the TalkJS MCP server delete data?
- Yes. 3 tools can delete, cancel or revoke something: delete_secret_key, update_secret_key and update_settings.
Can the TalkJS MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the TalkJS MCP server have?
- 8 tools: 3 destructive, 1 write, 4 read. delete_secret_key, update_secret_key, update_settings, create_secret_key, get_connection_status, get_secret_key, get_settings and list_secret_keys.
Does the TalkJS MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the TalkJS MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the TalkJS MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.