Greptile MCP

Live

OAUTH 2.1

CODE REVIEW

Developer Tools

Greptile MCP gives agents authenticated access to your code review data: list pull requests, inspect review comments, and trigger new Greptile code reviews.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Greptile MCP
agent · Acme Q3
Run
Which open PRs on acme/api have unaddressed Greptile comments?
S
greptilmcp_list_merge_request_comments
118ms
Greptile agent
4 open PRs have unaddressed comments. PR #212 has 3, flagged as high risk on auth changes.
Sources: 4 PRs, 11 comments
greptilmcp
4 PRs
18:29
Message Claude...

Tools your dev agent reaches for on Greptile, scoped per user.

CALL ANY TOOL
Review pull requests end to end: trigger a code review, read comments, and set custom review context for your org.
greptilmcp_list_pull_requests
List pull requests
List pull requests with optional filtering by repository, branch, author, and state.
Parameters
Name
Type
Required
Description
name
string
Optional
Filter by repository name, e.g. owner/repo.
state
string
Optional
Filter by merge request state: open, closed, or merged.
authorLogin
string
Optional
Filter by the author's login username.
greptilmcp_get_merge_request
Get merge request
greptilmcp_list_merge_request_comments
List review comments
greptilmcp_trigger_code_review
Trigger code review
greptilmcp_get_code_review
Get code review
greptilmcp_create_custom_context
Create custom context
Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Greptile tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["greptilmcp"], toolNames: [
    "greptilmcp_list_pull_requests",
    "greptilmcp_get_merge_request",
    "greptilmcp_list_merge_request_comments"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "List open PRs on acme/api with unaddressed review comments" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["greptilmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "List open PRs on acme/api with unaddressed review comments" }],
  tools,
});

// Execute the tool call with the user's vaulted greptilmcp credential
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["greptilmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "List open PRs on acme/api with unaddressed review comments" }],
  tools,
});

// Tool call runs with the user's vaulted greptilmcp credential
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["greptilmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "greptilmcp_agent",
  model: "gemini-2.5-pro",
  instruction: "Greptile tools scoped to this user",
  tools,
});

await agent.run("List open PRs on acme/api with unaddressed review comments");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Greptile MCP tool. Click to copy, paste into your agent, done.
PR review status
Copy the prompt
Copied
List open pull requests on acme/api.
Copy the prompt
Copied
Get merge request #212 on acme/api with its review analysis.
Copy the prompt
Copied
Which comments on PR #212 are still unaddressed?
Trigger and check reviews
Copy the prompt
Copied
Trigger a Greptile code review for PR #340 on acme/web.
Copy the prompt
Copied
Get the status of code review cr_9f21.
Copy the prompt
Copied
List code reviews for acme/api from the last week.
Org review policy
Copy the prompt
Copied
Create a custom context reminding reviewers to flag missing auth checks.
Copy the prompt
Copied
List all active custom context entries for the org.
Copy the prompt
Copied
Search Greptile comments mentioning 'SQL injection'.
SEE HOW AUTH WORKS
Your users connect once. Their Greptile MCP credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Greptile 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
Greptile 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
Greptile 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
Greptile 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 developer-tools connectors.
ENGINEERING
DevOps assistant agent
Triage GitHub incidents, open Linear tickets, and notify the on-call channel in Slack with context already attached.
ENGINEERING
Auto-release notes agent
Group merged GitHub PRs by feature, fix, or chore and publish release notes per tag. No manual changelog grooming.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought. Scalekit starts with identity, scope enforcement, and audit. Connectors follow.
01.
Shared tokens break per-user analytics
A shared Greptile MCP token looks fine in a demo. In production every code review looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Greptile MCP today. Ten connectors 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 Greptile MCP as the user or through a shared key?
As the user. Scalekit resolves the credential of the person who triggered the agent at request time, so every Greptile MCP action in your audit trail is attributed to a real user, not a shared service account.
Where is the Greptile MCP token stored?
In an AES-256 encrypted vault with per-tenant namespacing. Tokens are resolved at request time, never enter LLM context, refresh automatically, and can be revoked from one dashboard.
Can I limit what the agent does in Greptile MCP?
Yes. Filter by tool name in listScopedTools to expose only what you want. Scalekit also enforces scope checks before every API call.
What happens when a user revokes access?
The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.
Does Greptile MCP work across GitHub, GitLab, and Bitbucket?
Yes. Every tool takes a remote parameter (github, gitlab, azure, or bitbucket), so the same scoped tool set covers whichever hosting provider a repository uses.
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"": {
""greptilmcp"": {
""url"": ""https://mcp.scalekit.com/greptilmcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.greptilmcp]
url = ""https://mcp.scalekit.com/greptilmcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""greptilmcp"": {
""url"": ""https://mcp.scalekit.com/greptilmcp"",
""type"": ""http""
}
}
}