§ MCP · Model Context Protocol

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

Connector URLhttps://insightbridge-secondchair.aicolab.org/mcp

This report is public: no authentication is required.

Claude — personal accounts (Free, Pro and Max)
  1. Open Customize → Connectors.
  2. Click +, then Add custom connector; name it and paste the URL above.
  3. Leave Advanced settings empty and click Add.
  4. 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.

  1. An owner opens Organisation settings → Connectors and adds a custom web connector with the URL above.
  2. No authentication is required for this public report.
  3. Each member connects it from their own connector settings and switches it on in a chat.

Custom connector administration →

ChatGPT — custom MCP app
  1. Turn on Developer mode in Settings → Apps → Advanced settings, where your plan offers it; a workspace may need an administrator.
  2. Open Apps → Create and enter the URL above.
  3. Choose No authentication, scan the tools and create the app.
  4. Select the app in a conversation and ask about the record.

OpenAI's setup guide →

Microsoft 365 Copilot — via Copilot Studio
  1. Open an agent in Copilot Studio, then Tools → Add a tool → New tool → Model Context Protocol.
  2. Enter a name, a description of this record and the URL above. Choose None for authentication.
  3. Create the connection and add it to the agent. Test a question, then publish it.

Microsoft's connection guide →

Claude Code

Add the report as a remote HTTP server:

claude mcp add --transport http insightbridge-legal-ai https://insightbridge-secondchair.aicolab.org/mcp

Run /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_id is the topicClusterId a 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_audit tool returns each document's claims paired with the evidence basis it offers, the timeframe and conditions, and who is affected; era_drift traces 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…