@speakai/mcp-server 1.43.0 → 1.43.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -94,29 +94,21 @@ Then click Add.
94
94
 
95
95
  ### ChatGPT
96
96
 
97
- 1. Open ChatGPT → **Settings → Apps & Connectors → Advanced**
98
- 2. Turn on **Developer Mode** (required while Speak AI isn't yet listed in ChatGPT's app store; this lets you add it as a custom app)
99
- 3. Back on **Apps & Connectors**, click **Create** and paste `https://api.speakai.co/v1/mcp`
100
- 4. For **Authentication**, choose **OAuth**
101
- 5. ChatGPT opens a new tab to Speak AI. Sign in (or click **Confirm** if already logged in) to authorize. You'll be redirected back; close the tab and return to ChatGPT.
102
- 6. **Per-chat:** open a chat, click the **+** / connector menu, and enable **Speak AI** for that chat.
97
+ **[Install Speak AI in ChatGPT](https://chatgpt.com/plugins/plugin_asdk_app_6ac2ff7ad9b481918e5eef0343cf3c7b)**
98
+
99
+ 1. Open [Speak AI in ChatGPT](https://chatgpt.com/plugins/plugin_asdk_app_6ac2ff7ad9b481918e5eef0343cf3c7b) while signed in to ChatGPT
100
+ 2. Click **Install plugin**
101
+ 3. ChatGPT opens a new tab to Speak AI. Sign in (or click **Confirm** if already logged in) to authorize. You'll be redirected back; close the tab and return to ChatGPT.
102
+ 4. **Per-chat:** open a chat, click the **+** menu, and enable **Speak AI** for that chat.
103
103
 
104
104
  <details>
105
105
  <summary>What each step looks like (screenshots)</summary>
106
106
 
107
- **1. Connect screen in ChatGPT**: paste the connector URL and pick OAuth.
108
-
109
- ![ChatGPT connect screen](./assets/openai/1.connect.png)
110
-
111
- **2. Confirm and continue**: ChatGPT asks you to continue to Speak AI.
112
-
113
- ![ChatGPT continue to Speak](./assets/openai/2.connect-continue.png)
114
-
115
107
  **3. Authorize on Speak AI**: sign in or click Confirm if you're already signed in.
116
108
 
117
109
  ![Speak AI authorization screen](./assets/openai/3.speak-auth.png)
118
110
 
119
- **4. Connected**: Speak AI now shows in your ChatGPT connector list.
111
+ **4. Connected**: Speak AI now shows in your ChatGPT apps list.
120
112
 
121
113
  ![Speak AI connected in ChatGPT](./assets/openai/4.connected.png)
122
114
 
@@ -125,11 +117,10 @@ Then click Add.
125
117
  <details>
126
118
  <summary>Trouble connecting?</summary>
127
119
 
128
- A few things we've seen during early access:
129
-
130
120
  - **Authorization tab doesn't show a "you're connected" page**: if you land on the plain Speak AI dashboard with no confirmation, the authorization still went through. Close that tab and return to ChatGPT.
131
- - **"Connect" button keeps reopening the dashboard**: fully close and reopen ChatGPT, then check **Settings → Apps & Connectors**. Speak AI should already be listed there.
132
- - **"No actions available" inside a chat**: make sure Developer Mode is still on, and that you've enabled Speak AI from the per-chat connector menu (step 6 above).
121
+ - **Install keeps reopening the dashboard**: fully close and reopen ChatGPT, then check **Settings → Apps & Connectors**. Speak AI should already be listed there.
122
+ - **"No actions available" inside a chat**: make sure you've enabled Speak AI from the per-chat **+** menu (step 4 above).
123
+ - **Can't install plugins in your ChatGPT account**: ask your ChatGPT admin to allow Speak AI, or add it as a custom connector instead: **Settings → Apps & Connectors → Advanced**, turn on **Developer Mode**, click **Create**, paste `https://api.speakai.co/v1/mcp` and choose **OAuth**.
133
124
 
134
125
  Still stuck? Email [success@speakai.co](mailto:success@speakai.co).
135
126
 
@@ -455,9 +446,9 @@ SPEAK_API_KEY=your-key npx @speakai/mcp-server
455
446
  | `submit_chat_feedback` | Rate a chat response (thumbs up/down) |
456
447
  | `get_chat_statistics` | Get AI Chat usage statistics |
457
448
  | `export_chat_answer` | Export a conversation or answer |
458
- | `get_analysis_quote` | Check if a file can be analysed as audio/video and what it costs |
449
+ | `check_analysis_eligibility` | Check whether a file can be analysed as audio or video |
459
450
 
460
- `ask_ai_chat`, `retry_ai_chat` and `get_analysis_quote` register only with `aiChat: true` or `aiChatAnswerOnly: true`. The stdio server uses `aiChat`, where Speak's assistant can call other tools. The hosted endpoint uses `aiChatAnswerOnly`: for AI-assistant connections the assistant answers only from the person's recordings and does not take actions in other apps.
451
+ `ask_ai_chat`, `retry_ai_chat` and `check_analysis_eligibility` register only with `aiChat: true` or `aiChatAnswerOnly: true`. The stdio server uses `aiChat`, where Speak's assistant can call other tools. The hosted endpoint uses `aiChatAnswerOnly`: for AI-assistant connections the assistant answers only from the person's recordings and does not take actions in other apps.
461
452
 
462
453
  The automation tools, `build_automation`, `provision_inbound_webhook`, `get_inbound_webhook` and `get_webhook_attempts` register only with `automations: true`, and `get_voice_test_run` and `apply_voice_test_recommendation` only with `voiceTestRunDetails: true`. The stdio server includes them; the hosted endpoint does not, because automation steps can run actions in connected third-party apps. On the hosted endpoint, set up automations in the Speak AI web app.
463
454
 
package/dist/index.d.ts CHANGED
@@ -6,7 +6,7 @@ export interface RegisterOptions {
6
6
  localFileAccess?: boolean;
7
7
  /** Register the voice test-run tools (start, pause, resume, cancel, results). Defaults to true; pass false to leave them off. */
8
8
  voiceTestRuns?: boolean;
9
- /** Register ask_ai_chat, retry_ai_chat and get_analysis_quote. Speak's assistant behind them can call other tools. */
9
+ /** Register ask_ai_chat, retry_ai_chat and check_analysis_eligibility. Speak's assistant behind them can call other tools. */
10
10
  aiChat?: boolean;
11
11
  /** Register the same AI Chat tools with answer-only descriptions. For the hosted server: Speak runs chat from AI-assistant connections with read tools over the person's recordings only, and no actions in other apps. */
12
12
  aiChatAnswerOnly?: boolean;
package/dist/index.js CHANGED
@@ -7042,7 +7042,7 @@ function register7(server, client, options = {}) {
7042
7042
  "To continue a conversation, pass the promptId from a previous response.",
7043
7043
  "Returns a promptId \u2014 save it to continue the conversation with follow-up questions.",
7044
7044
  "Set analysisMediaId + analysisInput to have the model listen to the audio or watch the video instead of",
7045
- "reading the transcript alone; call get_analysis_quote first to check the file can be analysed that way.",
7045
+ "reading the transcript alone; call check_analysis_eligibility first to check the file can be analysed that way.",
7046
7046
  answerOnly ? "The assistant answers only from the person's Speak recordings: it can search them and chart what it finds, and it does not take actions in other apps." : "The assistant can also call other Speak AI tools and actions in the user's connected third-party apps (for example, sending a message), so a prompt can change data or send content outside this chat."
7047
7047
  ].join(" ");
7048
7048
  const askAiChatInputSchema = {
@@ -7138,7 +7138,7 @@ function register7(server, client, options = {}) {
7138
7138
  );
7139
7139
  if (aiChat) registerSpeakTool(
7140
7140
  server,
7141
- "get_analysis_quote",
7141
+ "check_analysis_eligibility",
7142
7142
  "Check whether a media file can be analysed as audio or video before running ask_ai_chat with analysisInput. Returns whether the file is eligible and, when it is not, a plain-English reason. An unavailable file is a normal result here, not an error. This is the only check that accounts for both the account's opt-in and the server-wide switch, so call it before an audio or video run.",
7143
7143
  {
7144
7144
  mediaId: import_zod8.z.string().min(1).describe("Media file to check"),
@@ -14035,7 +14035,7 @@ var init_tool_names = __esm({
14035
14035
  "get_live_meeting_transcript",
14036
14036
  // prompt
14037
14037
  "ask_ai_chat",
14038
- "get_analysis_quote",
14038
+ "check_analysis_eligibility",
14039
14039
  "list_prompts",
14040
14040
  "get_favorite_prompts",
14041
14041
  "toggle_prompt_favorite",
@@ -15333,7 +15333,7 @@ var SPEAK_MCP_TOOL_CATEGORIES = [
15333
15333
  "submit_chat_feedback",
15334
15334
  "get_chat_statistics",
15335
15335
  "export_chat_answer",
15336
- "get_analysis_quote"
15336
+ "check_analysis_eligibility"
15337
15337
  ]
15338
15338
  },
15339
15339
  {
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@speakai/mcp-server",
3
- "version": "1.43.0",
3
+ "version": "1.43.2",
4
4
  "mcpName": "io.github.speakai/mcp-server",
5
5
  "description": "Official Speak AI MCP Server — capture meetings, search thousands of recordings, run async voice and video surveys, create clips, and automate workflows from your AI assistant.",
6
6
  "homepage": "https://docs.speakai.co/mcp",