Give an agent the whole record
Every number and quote on these pages comes from a live query, and the same record is open to AI agents through a Model Context Protocol server. Add it as a connector and your agent can search every passage, read every topic and every source, compare what each voice says and follow every claim to its source document.
Add it as a connector
https://insightbridge-secondchair.aicolab.org/mcpThis report is public: no authentication is required.
Claude — personal accounts (Free, Pro and Max)
- Open Customize → Connectors.
- Click +, then Add custom connector; name it and paste the URL above.
- Leave Advanced settings empty and click Add.
- In a chat, click +, open Connectors and switch it on for that conversation.
Connectors are account-wide: added once, there in Claude on the web, desktop and mobile. Claude's connector guide →
Claude — organisation accounts (Team and Enterprise)
On Team and Enterprise plans only an organisation owner can add a custom connector; members do not see the option.
- An owner opens Organisation settings → Connectors and adds a custom web connector with the URL above.
- No authentication is required for this public report.
- Each member connects it from their own connector settings and switches it on in a chat.
ChatGPT — custom MCP app
- Turn on Developer mode in Settings → Apps → Advanced settings, where your plan offers it; a workspace may need an administrator.
- Open Apps → Create and enter the URL above.
- Choose No authentication, scan the tools and create the app.
- Select the app in a conversation and ask about the record.
Microsoft 365 Copilot — via Copilot Studio
- Open an agent in Copilot Studio, then Tools → Add a tool → New tool → Model Context Protocol.
- Enter a name, a description of this record and the URL above. Choose None for authentication.
- Create the connection and add it to the agent. Test a question, then publish it.
Claude Code
Add the report as a remote HTTP server:
claude mcp add --transport http insightbridge-legal-ai https://insightbridge-secondchair.aicolab.org/mcpRun /mcp in Claude Code to check the connection. Claude Code's MCP guide →
Then ask: “Using Second Chair, which topics have the widest reach, where do sources differ, and what verbatim quotes support their positions?”
Transport: Streamable HTTP, stateless JSON-RPC over POST https://insightbridge-secondchair.aicolab.org/mcp. The endpoint answers each request with JSON and keeps no SSE stream open.
How to read what comes back
- Counts describe this record. These are the sources in it, collected by hand for the AI and the Legal Profession research program; "N sources say X" measures the record, never a wider population.
- Positions are relative to each topic's own proposition. Supports, Builds on, Mixed, Redirects, Opposes, Unclear measure a stance toward one framing, not agreement with the report or with each other.
- One lens: Voice. Perspectives compare what each value of it says; the tools that take it list its values.
- Use the ids the tools return.
topic_idis thetopicClusterIda topic tool returns; source and source document tools return the ids their detail tools take. - Restricted works are analysed, never reproduced. A source whose distribution is restricted (paywalled or login-only) keeps its analysis, stances, key points and quotes, but no tool returns its passage text and passage search never finds it.
- The claim spine. The
claim_audittool returns each document's claims paired with the evidence basis it offers, the timeframe and conditions, and who is affected;era_drifttraces how positions move across the five ordinal eras. The evidence basis records what a document offers, not whether the claim is true. - Counts are not prevalence. This is a curated evidence base, not a survey: how many sources say something describes the collection, never the field.
Try the tools
Choose a tool, adjust its inputs and call the live server: the exact request an agent makes. The tools, their inputs and their example values come from the server itself.
Loading the tools…