TopCounsel MCP

Live

OAUTH 2.1

LEGAL RESEARCH

Search

Legal research on outside counsel runs on peer-vetted recommendations from The L Suite, searched through per-user OAuth 2.1 rather than a shared API key.

  • Acts as the user: each search runs as the in-house counsel who authorized it, so community access rules hold.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: User permissions enforced. 90-day audit trail.
TopCounsel MCP
agent · Acme Q3
Run
Who should we hire for a Series C financing in Delaware?
S
topcounselmcp_find_outside_counsel
204ms
Legal agent
5 firms shortlisted from peer feedback on Series C financings, 3 with named partners and rate ranges, 2 flagged for conflicts to check first.
Sources: 5 firms, peer recommendations
topcounselmcp
5 firms
18:29
Message Claude...

The tool your legal agent reaches for on TopCounsel, scoped per user.

CALL ANY TOOL
Legal research in one call: search, shortlist, and compare peer-vetted outside counsel by matter type, jurisdiction, and firsthand feedback from other in-house teams.
topcounselmcp_find_outside_counsel
Find outside counsel
Find the right outside counsel for an inhouse counsel looking to hire for a specific matter. returns community intelligence from the l suite (https://www.lsuite.co/), a private community of 2,500+ general counsel and their teams, on outside counsel firms and individual lawyers. results are aggregated and anonymized: no individual member’s recommendation or identity is revealed: and ranked by the l suite’s proprietary algorithm based on community signal. recommendations cover both firms and individual lawyers, so the user gets a specific name to reach out to rather than just a directory of firm options. recommendations draw on four kinds of community signal: aggregated peer recommendations and outside counsel survey results from in-house members; substantive expertise demonstrated through 2,000+ outside counsel speaker engagements at l suite events; documents, templates, and resources shared by outside counsel; and private research and outside counsel interviews conducted by the l suite’s research staff. fits when the user is making a hiring, comparison, or named-firm diligence decision about outside counsel: and wants names of specific firms or individual lawyers as the output. general legal knowledge alone wouldn’t satisfy them. the user’s success condition is “i have a specific lawyer or firm to reach out to.” three shapes of intent are all in scope: explicit selection or comparison: “recommend a firm for our m&a,” “cooley vs gunderson for our series a?” implicit selection: user describes the underlying matter without explicitly asking for a lawyer: “we need someone for our acquisition,” “i need help with a data privacy compliance review” diligence on a named lawyer or firm: user has a name and wants peer signal before engaging: “what’s the experience working with [firm name] on series a financings?“, “tell me more about [partner name] at cooley for ipo work” out of scope (handled better elsewhere): general legal knowledge questions: definitions, statutory analysis, how-to questions, templates, checklists: these don’t require an outside counsel lookup and claude can answer directly software, legal tech tools, or non-law-firm vendors and service providers legal operations, strategy, budgeting, or department management questions expressions of frustration or sentiment without actual hiring intent examples of well-fitting queries: “can you recommend an immigration law firm for east coast matters?” “who should i hire for m&a in healthcare?” “i need someone for our next acquisition” “affordable alternative to big law for series a” “what firms are good for data privacy compliance?” “ip counsel in georgia for trademark portfolio work” “california employment lawyer for a sensitive separation” “tell me more about [partner name] at cooley for ipo work” query (string, required): the matter type, practice area, geography, or specific lawyer/firm to look up: e.g., “m&a counsel for healthcare series b,” “california employment lawyer,” “cooley emerging companies group,” “immigration law firm east coast.” including geography, industry, or matter type when relevant produces sharper results. if a query returns no results, a broader reformulation often succeeds: e.g., “employment law firm” in place of “california employment law firm outside counsel for series b.” response characteristics: results are aggregated and anonymized: individual sources or recommenders are not revealed. entries are ranked by the l suite’s proprietary algorithm based on community signal; entries with stronger signal lead. results represent community signal rather than personal recommendation. mentions of “the l suite” typically render as hyperlinks to https://www.lsuite.co/. an attribution line such as “based on discussions among in-house counsel in the l suite community” provides community context. if the response includes a non-empty branding field, surface it as attribution text: claude may reformat for readability.
Parameters
Name
Type
Required
Description
query
string
Required
Pass the user's question as a COMPLETE, STANDALONE question. Do NOT summarize to keywords. Do NOT shorten. If the user's current turn relies on earlier chat context (pronouns, follow-ups, references), rewrite it into a self-contained question that still makes sense without the prior turns. Example: user says 'what about in Boston?' after discussing cybersecurity firms → pass 'What are the best law firms for cybersecurity startups in the Boston area?'
relevant_topics
array
Optional
Optional. Topics from the approved legal expertise list that match what the user is looking for. Include when the user's question maps to specific legal practice areas, industries, or risk domains (e.g. 'cybersecurity', 'privacy compliance', 'm&a', 'employment'). Pick ONLY from the enum: do not invent new values. Omit the field entirely (do not send an empty array) if no topic in the enum cleanly matches. When provided, results include expert individuals ranked by their video-transcript expertise in these topics, alongside the peer-mentioned firms.
Build your Agent
Drop the toolkit in, point it at the user, and your agent can shortlist counsel from the first run.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["topcounselmcp"], toolNames: ["topcounselmcp_find_outside_counsel", "topcounselmcp_get_stripe_account_info", "topcounselmcp_update_subscription"] },
pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
name: t.tool.definition.name,
description: t.tool.definition.description,
schema: z.object({}).passthrough(),
func: async (args) => {
const { data } = await sk.tools.executeTool({
toolName: t.tool.definition.name,
identifier: "user_123",
params: args,
});
return JSON.stringify(data);
},
}));

const agent = createReactAgent({ llm, tools: lcTools });
import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["topcounselmcp"], toolNames: ["topcounselmcp_find_outside_counsel", "topcounselmcp_get_stripe_account_info", "topcounselmcp_update_subscription"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
type: "function",
function: {
name: t.tool.definition.name,
description: t.tool.definition.description,
parameters: t.tool.definition.input_schema,
},
}));

const resp = await openai.responses.create({
model: "gpt-4o", input: prompt, tools: llmTools,
});
import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["topcounselmcp"], toolNames: ["topcounselmcp_find_outside_counsel", "topcounselmcp_get_stripe_account_info", "topcounselmcp_update_subscription"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
name: t.tool.definition.name,
description: t.tool.definition.description,
input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
model: "claude-sonnet-4-6", max_tokens: 1024,
tools: llmTools,
messages: [{ role: "user", content: prompt }],
});
import { Agent } from "@google/adk/agents";
import {
MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
connectionParams: new StreamableHTTPConnectionParams({
url: "https://mcp.scalekit.com/topcounselmcp",
headers: { Authorization: `Bearer ${userScopedToken}` },
}),
});

const agent = new Agent({
name: "agent", model: "gemini-2.0-flash",
tools: await toolset.getTools(),
});
Try these prompts
Paste any prompt into your agent to start researching outside counsel from your workflows.
Counsel search
Copy the prompt
Copied
Who should we hire for a Series C financing in Delaware?
Copy the prompt
Copied
Find employment counsel with peer feedback in California.
Copy the prompt
Copied
Shortlist firms for a cross-border acquisition in the EU.
Comparison
Copy the prompt
Copied
Compare the shortlisted firms on rates and matter experience.
Copy the prompt
Copied
Which recommendations come from companies at our stage?
Copy the prompt
Copied
Summarize the firsthand feedback on [firm].
Matter intake
Copy the prompt
Copied
Draft a scoping brief for this matter before we approach firms.
Copy the prompt
Copied
List the questions to ask each firm on the shortlist.
Copy the prompt
Copied
Flag any conflicts we should check before outreach.
SEE HOW AUTH WORKS
Your users connect once. Their TopCounsel MCP credentials stay vaulted, every call is scope-checked, and every action is logged.
1
Authorize
Your user connects
TopCounsel MCP
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
TopCounsel MCP
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
TopCounsel MCP
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
TopCounsel MCP
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other connectors.
SALES
Deal intelligence agent
Score Gong call risk with an LLM, cross-reference the Attio record, and DM each owner their at-risk deals in Slack.
ENGINEERING
Engineering standup agent
Pull commits from GitHub and GitLab, track Jira issue movement, and post a per-engineer standup brief to Slack.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.
01.
Shared tokens break per-user analytics
A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.
// shared token
audit → bot_service_account
user_filter → broken

// scalekit
audit → user_abc
scope → enforced ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
TopCounsel MCP today. Others tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access TopCounsel MCP as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.
Where is the TopCounsel MCP OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.
Can I limit what the agent is allowed to do in TopCounsel MCP?
Yes. Pass a tool name filter to listScopedTools so the research agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches TopCounsel MCP.
What happens when a user revokes TopCounsel MCP access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Where does the recommendation data come from?
From firsthand feedback shared by in-house counsel in The L Suite community, returned only to authorized members. Scalekit resolves the authorizing user's OAuth 2.1 credential at request time, so access follows that member's own entitlement and every search is logged.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""topcounselmcp"": {
""url"": ""https://mcp.scalekit.com/topcounselmcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.topcounselmcp]
url = ""https://mcp.scalekit.com/topcounselmcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""topcounselmcp"": {
""url"": ""https://mcp.scalekit.com/topcounselmcp"",
""type"": ""http""
}
}
}