The AI Agent Layer for Indian Law: Harvey, MCP and the Court Data Gap

What an AI legal agent is made of, how MCP connects it to Indian court data, who is building, what courts’ AI rules say, and why retrieval decides quality.

The AI agent layer for Indian law, cover design variant A for the eCourtsIndia blog

Last updated: 16 November 2026

An AI legal agent for Indian law is built from four parts: a foundation model, a retrieval layer of court and statute data, an orchestration layer, and a workflow interface. In India the retrieval layer is the real bottleneck, because clean, current, nationwide court data is hard to get. The Model Context Protocol (MCP), an open standard now supported by Anthropic, OpenAI and Google, is a widely adopted way to wire that data into an agent.

Legal AI has moved from novelty to a line item in legal budgets. On 9 September 2026 Harvey raised USD 550 million at a USD 15.5 billion valuation, led by Diffusion and Lightspeed, up from USD 11 billion in March 2026 (Harvey). Hebbia raised a USD 130 million Series B led by Andreessen Horowitz in July 2024 (as reported).

Thomson Reuters completed its USD 650 million cash acquisition of Casetext, maker of CoCounsel, in August 2023. Clio completed its USD 1 billion acquisition of vLex in November 2025. The agent layer for legal work is real and well funded. The question for India is what its stack will look like.

Key takeaways

  • A legal agent is model + retrieval + orchestration + workflow. The model is the easiest part to swap.
  • Many early legal AI failures are data failures: invented citations, missed recent orders, merged parties, missing district courts.
  • MCP, open-sourced by Anthropic in November 2024 and now a Linux Foundation project, lets any compatible agent call an external data source through one shared contract.
  • The eCourtsIndia MCP server exposes 41 tools across four datasets: cases and orders, district and taluka cause lists, a statute book of 10,000+ Acts, and the electoral roll.
  • The global money is going to workflow companies such as Harvey. In India, whoever builds the workflow will still need a court-data layer underneath.

This post covers the anatomy of a legal agent, what MCP is, what is different about India, who is building, why the data layer is the bottleneck, what Indian courts say about AI, and the checklist an Indian legal MCP server has to meet.

The AI agent layer for Indian law: model, retrieval, orchestration and workflow, with Indian court data as the bottleneck

What is an AI legal agent?

Strip away the marketing, and a legal AI agent is four things.

  1. A foundation model. GPT, Claude, Gemini or a fine-tuned variant. Any of these can be the reasoning engine, and Harvey has even started post-training its own.
  2. A retrieval layer. Access to case law, statutes, court records and the client’s own matter data. This is where court data lives.
  3. Orchestration. The prompts, guardrails and multi-step logic that let the agent plan, execute, verify and report.
  4. A workflow interface. Where the lawyer actually works: a document editor, a matter screen, a chat window, a review pane.

The foundation model is not the moat (an advantage competitors cannot easily copy). Builders switch models in an afternoon. The retrieval layer is a moat because it depends on data access and quality. Orchestration and workflow are moats because they depend on domain expertise and product work. In our view, the winners in each market will be strong on all three non-model layers. We argued the same point from the data side in data moats when LLMs are a commodity.

What is MCP and why does it matter for legal AI?

The Model Context Protocol is an open standard that lets an AI model call external tools and data sources through a shared contract, so an agent can reach current court data without custom scraping or a bespoke integration. Anthropic published the specification in November 2024. In December 2025 Anthropic donated MCP to the Agentic AI Foundation, a Linux Foundation project whose members include OpenAI, Google and Microsoft.

It is a contract, like HTTP, not a product. Anyone can build a server that speaks MCP and anyone can build a client that calls it. Claude supports it natively, and OpenAI and Google have added MCP support to their agent tooling since. For a legal team, the practical effect is that the AI tool they already use gains the ability to answer questions about real Indian matters. Our MCP 101 for legal teams is the longer primer, and the step-by-step connect guide shows the setup in Claude.

How is Indian law different for AI agents?

  • The corpus is large. Over 5.6 crore cases were pending across Indian courts in July 2026, about 4.99 crore of them in district and taluka courts, according to the Law Ministry’s reply in the Lok Sabha. Our own index holds 30 crore+ case records, each with its orders and judgments where the court has uploaded them, and much of India’s case law is multilingual.
  • The public data layer is open. The Government’s eCourts services, the National Judicial Data Grid (NJDG) dashboards and High Court websites publish case status, orders and cause lists free of charge, though there is no official public bulk API. That lowers the cost of getting data for Indian builders. eCourtsIndia (ecourtsindia.com) is an independent, non-government platform, not the Government’s eCourts portal (ecourts.gov.in) and not affiliated with any court.
  • The language question is real. Orders in many states are in regional languages. A national agent has to handle Hindi, Marathi, Tamil, Telugu, Bengali and more. That is an obstacle today and a moat for whoever solves it.
  • The professional context varies widely. A Supreme Court senior counsel’s day looks nothing like a district court solo practitioner’s. One agent will not fit both. Vertical agents by court tier, matter type and buyer are more likely to win.
  • Tribunals matter. Much commercially important litigation sits in the NCLT, DRTs, ITAT and consumer commissions. These tribunals run their own portals, outside the regular court system and the official eCourts CNR numbering. Their orders can still reach the High Courts or the Supreme Court, often after a further appeal to a body such as the NCLAT or DRAT. eCourtsIndia assigns its own 16-character CNR-style ID to cases from 14 tribunals, including these four.

Who is building legal AI agents?

We name names carefully and only from public information. For the longer arc, see a short history of Indian legaltech.

CompanyWhat it doesPublic signal
HarveyLegal AI workflows for law firms and in-house teams; publicly multi-modelUSD 550 million at USD 15.5 billion valuation (Sep 2026); used by 80% of Am Law 100 firms (company claim)
HebbiaAgentic document analysis for finance and legal workUSD 130 million Series B led by Andreessen Horowitz (Jul 2024)
LegoraCollaborative AI platform for lawyers; offices include BengaluruUSD 550 million Series D at USD 5.55 billion valuation (Mar 2026)
LexisNexis ProtégéAgentic AI assistant inside Lexis+Lexis+ with Protégé replaced Lexis+ AI in the US (Feb 2026)
Thomson Reuters CoCounselLegal AI assistant built from the Casetext acquisitionCasetext acquired for USD 650 million in cash (completed Aug 2023)
Clio and vLexPractice management plus legal research and AIClio acquired vLex for USD 1 billion (completed Nov 2025)
AnthropicFrontier model maker with an open-source legal plugin for ClaudePlugin skills to review contracts, triage NDAs, check compliance, assess risk and prepare for meetings
Lucio (Bengaluru)AI workspace for lawyersFunding figures not independently verified
LegitQuest, CaseMineAI-assisted research on Indian case lawLive products on Indian judgments
SpotDraft, LawrbitContract management and regulatory compliance software with AI featuresLive products for in-house teams
Selected legal AI builders and the public record behind each, as of September 2026. Company figures are from company announcements or named press reports, listed under Sources.

Whoever wins on orchestration and workflow, every one of them will need clean Indian court data to serve Indian matters. That is the layer every one of them will have to buy or build. For the investor view, see why Indian legal AI is a ten billion dollar category, our read of the Clio and vLex deal and where Indian legaltech funding has gone.

Why is court data the bottleneck for legal AI in India?

A legal AI agent is only as reliable as its retrieval layer. In practice, many failures in early legal AI start with the data rather than the model.

  • The agent cites a case that does not exist. Grounding retrieval in a verified corpus reduces this risk, but does not remove it. A May 2024 Stanford study found retrieval-based legal research tools still hallucinated on more than 17% of test queries, so every citation still needs checking. We tested which AI assistants get Indian court answers right.
  • The agent misses a recent adverse order because its data was refreshed a month ago.
  • The agent merges two parties with similar names because the data had no entity resolution. See same-name false positives in court records.
  • The agent cannot see district or taluka courts, or tribunals, because its retrieval layer only covers the Supreme Court and High Courts.

Each of these makes an agent dangerous in legal work. A lawyer cannot send a client a memo citing cases that do not exist. A partner cannot sign off on due diligence built on a litigation profile that missed half the states. The fix is architectural: the retrieval layer has to be current, authoritative, national and structured, which is why we set out how eCourtsIndia structures each case into fields. Our map of India’s court data stack shows where that data comes from. A foundation model does not provide it. A purpose-built data platform does, which is why we built the eCourtsIndia MCP server.

What must an Indian legal MCP server do?

Building an MCP server is easy. Building one that is useful for Indian legal work is hard. Here is the minimum bar, and where the eCourtsIndia server stands on each point (October 2026).

RequirementWhy it matterseCourtsIndia MCP today
Unified entitiesOne advocate or company should be one handle, across courts and spellingsParties, petitioners, respondents, advocates and judges are separate searchable fields across the whole index
Cross-court searchOne call, across courts and tribunalssearch_cases covers the Supreme Court, all 25 High Courts, district and taluka courts, and 18 tribunal and commission types
Freshness on demandCourt data goes stale fastrefresh_case, and bulk_refresh_cases for up to 50 CNRs per request; a case typically lands in 2 to 10 minutes
Structured ordersAn order is an object, not just a PDFOrders as text through get_order_markdown, AI analysis of an order, and the statute provisions a case cites
Cause-list integrationNo lawyer workflow works without tomorrow’s boardcheck_cnr_causelist checks up to 100 CNRs in one call; cause lists cover district and taluka courts, not High Courts or tribunals
Grounding in the statuteAgents should quote the law, not remember itA statute book of 10,000+ Acts (911 Central, 9,175 State, most State Acts read by OCR from scanned gazettes) and 2.7 lakh+ sections, with IPC to BNS, CrPC to BNSS and IEA to BSA mappings; these tools are charged per section, like the rest of the API
ProfilesJudges, advocates and litigants linked to their casesSearch by judge, advocate or litigant name; public judge pages list the same matters
Clear dataset boundariesMixing datasets is a common agent errorFour datasets kept apart: cases and orders, cause lists, statutes, and the electoral roll, each with its own codes
Predictable accessAgents need auth and pricing they can reason aboutOAuth sign-in at mcp.ecourtsindia.com/mcp; data tools, including the statute book, are credit-metered; discovery lookups are free
Checklist for an Indian legal MCP server, with the eCourtsIndia MCP status in October 2026 (server documentation).

Two items are still open, and we would rather say so. Regional-language text in older scanned orders is not yet uniformly searchable, and High Court and tribunal cause lists are not in the cause-list dataset. An agent built on any Indian court-data source should be told about gaps like these, so it can say “not in the data” rather than “no hearing”.

The statute book, IndiaCode by eCourtsIndia, deserves a note. Anyone can read it free on the site, with Markdown and Akoma Ntoso versions of each provision, and developers can ground an agent in bare Act text through the Acts and Sections endpoints of the eCourtsIndia API, which our complete API guide documents.

Example: a weekly litigation brief for an in-house team

Illustrative example: take an in-house counsel at a mid-sized Indian NBFC who asks Claude for a weekly brief on all active litigation against the company. The company is hypothetical, but every step uses real tools.

Without a data connection, Claude can only write a template, because its knowledge stops at its training cutoff. With the eCourtsIndia MCP server connected, Claude searches for matters where the company is petitioner or respondent, gets back CNRs, statuses, next hearing dates, advocates and the latest orders, and checks the district-court matters against upcoming cause lists in one batch. It then writes the brief the General Counsel actually needs: which matters are listed this week, which had new orders, where the bench changed, and which new filings appeared.

The lawyer did not write a query or learn a new tool. The model does the reasoning, MCP connects it to data, and court records are what it reasons over. We walk through this in detail in the General Counsel portfolio playbook, and the solo-practice version is One Advocate, Nine Courts, One Claude Window. The morning cause-list version is in the 5 AM cause list problem.

What changes for advocates, in-house teams, founders and enterprises

  • For the practising advocate: the workflow moves from many portals to one window, and we explain why data, not adoption, is the bottleneck for Indian lawyers. If you would rather not assemble your own agent, the AI Clerk is eCourtsIndia’s own agent for lawyers (meet the AI Clerk). The Chrome Extension adds ₹100 of free credit a month while it is active, and paid plans start at ₹250 + 18% GST a month (at the time of writing, November 2026).
  • For in-house counsel: the Friday spreadsheet becomes a prompt, and new filings against the company surface within days rather than at the next hearing.
  • For legal AI founders: building on an existing court-data API is far cheaper than maintaining your own scrapers. Engineering time goes to product, sales and language support instead of portal maintenance.
  • For enterprise buyers: BGV firms, lenders and insurers move from manual lookups to API and MCP integration, or use a finished product such as LegalCheck. Developers can start from the LegalCheck API for background checks or build a due diligence engine on the API.

What do Indian courts’ AI rules mean for agent users?

On 3 June 2026 the Hon’ble Supreme Court of India published draft Regulations for Use of Artificial Intelligence in Courts, 2026, for public comment. The draft would require advocates to declare when they used AI. It also says no judicial outcome may rest on algorithmic decision-making alone.

In November 2025 the Hon’ble Supreme Court’s Centre for Research and Planning released a white paper on AI in the judiciary. It calls for a human in the loop and records fake-citation incidents, including in a Karnataka trial court and a recalled ITAT order.

The Hon’ble Kerala High Court’s policy of 19 July 2025 bars the district judiciary under its control from using AI tools to arrive at any findings, reliefs, orders or judgments.

For anyone using a legal agent in India, the practical rule is simple: treat AI output as a draft, verify every citation against the court record, and disclose AI use where rules require it.

What this means for eCourtsIndia

Disclosure: eCourtsIndia sells the API, MCP server and AI Clerk described in this section.

Our role is to supply the court and statute data that agents need. We maintain the retrieval layer others can build on: 30 crore+ case records with their orders and judgments, searchable advocate, judge and litigant directories, and a statute book. These are exposed through a REST API with 32 documented endpoints and ₹200 in free signup credits (at the time of writing, November 2026), and through an MCP server with 41 tools. We also ship one agent of our own, the AI Clerk, for lawyers who want a finished product rather than a stack.

Our advice to anyone building a legal agent for India: do not try to own the foundation model. Pick a model, invest in orchestration and workflow, and build on a data layer you can verify. That approach has drawn large investments in legal AI abroad, and we think it suits India too. The broader architecture is in The Operating System for Indian Law.


Connect the eCourtsIndia MCP server to your agent, read the API documentation, or search any case free at ecourtsindia.com/search.

Related reading

Frequently Asked Questions

What is an AI legal agent?

An AI legal agent is software that plans and carries out legal tasks, not just answers questions. It has four parts: a foundation model such as Claude, GPT or Gemini; a retrieval layer of case law, statutes and court records; an orchestration layer that breaks work into steps and checks them; and a workflow interface where the lawyer reviews the output.

Why do AI legal tools invent case citations?

Usually because the model answers from memory instead of a verified record. Retrieval from a real court database lowers the risk but does not remove it: a 2024 Stanford study found retrieval-based legal research tools still hallucinated on more than 17% of test queries. Every citation an AI produces must be checked against the actual order before it goes into a filing.

What is MCP in legal AI?

The Model Context Protocol (MCP) is an open standard that lets an AI assistant call outside tools and data through one shared contract. Anthropic released it in November 2024 and donated it to the Linux Foundation’s Agentic AI Foundation in December 2025. For lawyers, it means an assistant like Claude can query current court records instead of relying on what it remembers.

Is there an official API for Indian court data?

No. The government’s eCourts Services portal and the National Judicial Data Grid publish case status, orders and cause lists free, but there is no official public bulk API. Private platforms such as eCourtsIndia, an independent non-government service, offer paid APIs and an MCP server built on that published data. They mirror official sources and can lag them, so verify critical details on the court portal.

Can lawyers in India use AI tools in court work?

There is no blanket ban, but rules are arriving. The Supreme Court’s draft Regulations for Use of Artificial Intelligence in Courts, 2026, published for comment in June 2026, would require advocates to declare AI use and say no judicial outcome may rest on algorithmic decision-making alone. The Kerala High Court’s July 2025 policy bars its district judiciary from using AI to reach findings.

How much is Harvey AI valued at?

Harvey, the US legal AI company, raised USD 550 million at a USD 15.5 billion valuation on 9 September 2026, in a round led by Diffusion and Lightspeed. Its previous round, in March 2026, valued it at USD 11 billion. Harvey says 80% of Am Law 100 firms use it, which is the company’s own claim.

What should an Indian legal MCP server cover?

At minimum: one search across the Supreme Court, High Courts, district courts and tribunals; on-demand refresh of stale cases; orders as readable text; cause-list checks; statute text with IPC to BNS mappings; judge, advocate and litigant search; and clear limits, so the agent can say “not in the data” instead of “no hearing”. It also needs predictable sign-in and pricing.

Sources

External sources checked 28 September 2026; eCourtsIndia product facts re-checked 12 October 2026.

eCourtsIndia is a private legal-technology platform. It is not affiliated with, associated with, or endorsed by the Government of India, the Supreme Court of India or its e-Committee, or any court. Official case information is published on ecourts.gov.in. Always verify details against official court records or certified copies. This article is general information, not legal advice. Spotted an error? Write to support@ecourtsindia.com.

Search 35 crore+ Indian court case records, free

One search across the Supreme Court, all 25 High Courts, district courts and 18 tribunal and commission types. Hearing alerts, AI summaries and an API for developers.