> SpecStream is the live web data engine for teams and agents. This is the Markdown copy of https://specstream.ai/docs/integrations/chatlima. Every page, with what SpecStream does and costs: https://specstream.ai/llms.txt # ChatLima Add SpecStream to ChatLima as a Streamable HTTP MCP server. Your chats can search the web, read pages and ask for live web data on your SpecStream balance, with the source URL of every answer. [SpecStream for ChatLimaAI assistants](https://specstream.ai/integrations/chatlima.md) ## What you need - ChatLima, at chatlima.com or on your own server, with a model that calls tools. - A SpecStream account. New accounts start with $10 of credit, no card. [Create one](https://specstream.ai/signup?utm_source=chatlima). 1. 1 ## 1. Create a SpecStream API key In SpecStream, open [Agents & API](https://specstream.ai/workspace/agents?tab=keys&utm_source=chatlima), choose **API keys**, then **Create API key**. Give it execute permission and a spending limit above zero, so it can search and run requests. Copy the key. 2. 2 ## 2. Open the server list In ChatLima, click **Settings** in the sidebar, open the **MCP Servers** tab and click **Manage Servers**. The **MCP Server Configuration** dialog opens. Click **Add Server**. 3. 3 ## 3. Enter the server Fill in the form as below. Choose **Streamable HTTP** under **Transport Type**, because SpecStream's server speaks Streamable HTTP. Leave **Use OAuth Authentication** unchecked: the key in the next step signs ChatLima in. MCP Server Configuration ```text Server Name: specstream Display Title (Optional): SpecStream Transport Type: Streamable HTTP Server URL: https://api.specstream.ai/mcp ``` 4. 4 ## 4. Add the key as a header Open **HTTP Headers**. Enter `Authorization` as the **Key** and `Bearer` followed by a space and your key as the **Value**, then click the **+** button. ChatLima hides the value in the list, because the header's name holds "Auth". Click **Add Server**. **Test Connection** checks only that the URL is well formed; ChatLima opens the connection, and SpecStream checks the key, the first time a chat uses a tool. HTTP Headers ```text Key: Authorization Value: Bearer YOUR_SPECSTREAM_API_KEY ``` 5. 5 ## 5. Turn it on and ask In the server list, click **Enable Server** on SpecStream. It then reads **Active**, and its tools are available to your chats. Ask a question that needs today's web: In a ChatLima chat ```text Search the web with SpecStream: what did the European Central Bank decide at its last meeting? Give the source URL. ``` ## What the chat can call - `search_web` answers a question from the live web: the answer as the page prints it, the page it was read from and the ranked results with their URLs. Each search of up to 10 results is $5 per 1,000 searches. - `read_pages` returns the main text of up to 20 pages or documents (PDF, Word, Excel) per call, at $0.80 per 1,000 pages. A page that gives no text is not charged. - `compile`, `quote_capacity_work` and `authorize_capacity_work` run Deep Search: a request in plain words returns every match on the live web as structured rows. SpecStream quotes the most it can cost, and nothing runs until you approve that amount. ## Beside ChatLima's own web search ChatLima's **Web Search** runs through OpenRouter and costs 5 credits a search. On the $9 monthly plan of about 1,000 credits, that is about 4.5¢ a search. Its `web_fetch` tool reads public URLs into the chat. Through SpecStream, a search is $5 per 1,000 and a page read is $0.80 per 1,000, from your SpecStream balance, whichever model the chat runs. The Search API is the most accurate web search API on SimpleQA Verified and WideSearch ([scores and method](https://specstream.ai/benchmarks.md)), and every answer names the page it was read from. ## Why an API key and not OAuth ChatLima's OAuth sign in asks for `openid profile email offline_access`: your identity, not permission to search or run requests. A token from it can't use SpecStream's tools, so connect with the key in the `Authorization` header. The key carries the spending limit you gave it. ## Where the key is kept ChatLima keeps the server list, headers included, in your browser's local storage. On another browser or device, add the server again with the same key, or with a key of its own so you can revoke one without the other. ## Cost Connecting SpecStream to ChatLima is free. Searches and page reads come out of your balance with no quote and no approval, and a search that returns no results costs nothing. A Deep Search row costs 5¢, 15¢ or $1, depending on how much the row needs, plus 5¢ for a person's email and 15¢ for a phone. A run can't cost more than the maximum you approved, and a run that finds nothing costs nothing. [Balance, quotes, and billing](https://specstream.ai/docs/billing.md) has the details. ## Disconnect In **Manage Servers**, click **Active** on SpecStream to turn it off for your chats, or click the trash icon (**Remove server**) to delete the entry. To end the key's access, revoke it under **API keys** in [Agents & API](https://specstream.ai/workspace/agents?tab=keys&utm_source=chatlima). Questions go to [support@specstream.ai](mailto:support@specstream.ai). ## More [SpecStream for ChatLima](https://specstream.ai/integrations/chatlima.md) covers what it does in ChatLima on one page. Every other tool has its guide in [Connect your tools](https://specstream.ai/docs/integrations.md). You see the most a request can cost before it starts, and the matches are paid from your balance. [Billing](https://specstream.ai/docs/billing.md) has the details. For help, email [support@specstream.ai](mailto:support@specstream.ai).