ktx/packages/cli/test/mcp-http-server.test.ts

275 lines
7.9 KiB
TypeScript
Raw Permalink Normal View History

feat(mcp):added MCP server (#97) * docs(specs): design research-agent MCP tools and ktx mcp daemon Adds the 2026-05-14 design spec for exposing four new MCP tools (discover_data, entity_details, dictionary_search, sql_execution), shipping a ktx-research skill, and introducing an HTTP-only ktx mcp daemon so external agents can use KTX as a research-capable context layer. * Refine research-agent MCP tools spec after adversarial review iteration 1 * Refine research-agent MCP tools spec after adversarial review iteration 2 * Refine research-agent MCP tools spec after adversarial review iteration 3 * Refine spec: drop connectionName compat carve-out and ground summary/snippet provenance per kind * feat(daemon): validate read-only SQL with sqlglot * feat(context): expose read-only SQL validation port * feat(context): register MCP sql execution tool * feat(context): execute MCP SQL through validated connector path * test(context): update SQL analysis port fixtures * docs: add research-agent MCP sql execution foundation plan * feat(context): add scan-backed entity details service * feat(context): register MCP entity details tool * feat(context): expose local MCP entity details * test(context): align entity details scan fixtures * docs: add research-agent MCP entity_details plan * feat(context): add dictionary search service * feat(context): register MCP dictionary search tool * feat(context): expose local MCP dictionary search * docs: add research-agent MCP dictionary_search plan * feat: add MCP discover data service * feat: expose discover data MCP tool * feat: wire local discover data MCP port * docs: add research-agent MCP discover_data plan * feat(cli): add mcp http security helpers * feat(cli): host mcp over streamable http * feat(cli): manage mcp daemon lifecycle * feat(cli): add ktx mcp commands * fix(cli): stabilize mcp daemon verification * docs: add research-agent MCP http daemon plan * feat(cli): install KTX research skill * feat(cli): configure MCP clients in setup agents * feat(cli): support Claude local MCP setup scope * docs: add research-agent MCP setup-agents plan * refactor(context): use connectionId in warehouse verification tools * docs(context): update ingest verification prompts for connectionId * docs: add research-agent MCP ingest contract convergence plan * chore: build runtime artifacts in conductor setup --------- Co-authored-by: Andrey Avtomonov <7889985+andreybavt@users.noreply.github.com>
2026-05-15 02:35:09 +02:00
import { request } from 'node:http';
import type { AddressInfo } from 'node:net';
import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
import { describe, expect, it } from 'vitest';
import {
buildMcpSecurityConfig,
isMcpRequestAuthorized,
normalizeHostHeader,
runKtxMcpHttpServer,
test: split cli tests from source tree (#216) * feat(cli): define full warehouse dialect contract * test(cli): keep dialect edge tests focused * fix(cli): stabilize dialect contract foundation * refactor(connectors): own read-only query preparation * refactor(connectors): resolve dialects through registry * refactor(connectors): keep concrete dialect classes internal * chore(workspace): enforce dialect import boundary * refactor(cli): resolve relationship dialect at scan boundary * refactor(cli): use dialect display parsing for entity details * refactor(cli): use dialect display parsing for warehouse catalog * refactor(cli): use dialect SQL in relationship workflows * test(cli): verify solid dialect scan workflow closure * test: split cli tests from source tree * refactor(cli): standardize BigQuery scope listing * feat(sqlite): implement connector scope listing * test(connectors): cover required table listing * feat(cli): add warehouse driver registry * refactor(setup): route scope discovery through driver registry * refactor(cli): route local query execution through driver registry * refactor(historic-sql): route dialect support through driver registry * refactor(cli): test warehouse connections through driver registry * fix(cli): close driver registry type export gaps * Improve setup daemon diagnostics * refactor(setup): centralize rail-prefixed diagnostics + query-history fallback Extract errorMessage, writePrefixedLines, and flushPrefixedBufferedCommandOutput into clack.ts so the setup wizard, managed daemons, and embedding/agent steps share one rail-formatted writer. setup-databases.ts also adds a "disable query history and retry" option when the schema-context build fails and query history is the likely culprit, surfaced via a new failed-query-history-unavailable status. * fix(cli): carry catalog through the picker so BigQuery/Snowflake/SQL Server scope filters match The setup picker's KtxTableListEntry was a 2-level { schema, name }, so qualifiedTableId always wrote db.name into enabled_tables. When BigQuery, Snowflake, or SQL Server later ran fast ingest, their introspect step filtered the scope set with scopedTableNames(scope, { catalog: projectId|database, db }) — catalog was non-null on the introspect side but null in the scope refs, so every entry was rejected, the live-database adapter staged zero table files, and detect() failed with 'Adapter "live-database" did not recognize fetched source output'. Align the picker boundary with the canonical 3-level KtxTableRef: - Add catalog: string | null to KtxTableListEntry. - BigQuery/Snowflake/SQL Server listTables populate catalog from the resolved projectId / database; Postgres/MySQL/ClickHouse/SQLite set null. - qualifiedTableId emits catalog.schema.name when catalog is non-null (resolveEnabledTables already accepts the 3-part shape) and schemasFromEnabledTables now goes through parseDottedTableEntry so it recovers the schema correctly from both 2-part and 3-part entries. - Export parseDottedTableEntry from enabled-tables.ts (@internal) for picker reuse. Update listTables expectations in all seven connector tests and the setup / picker test fixtures. Add a picker regression test that covers the catalog-bearing round-trip (save + refine). * fix(cli): allow debug telemetry under opt-out env
2026-05-26 08:49:05 +02:00
} from '../src/mcp-http-server.js';
feat(mcp):added MCP server (#97) * docs(specs): design research-agent MCP tools and ktx mcp daemon Adds the 2026-05-14 design spec for exposing four new MCP tools (discover_data, entity_details, dictionary_search, sql_execution), shipping a ktx-research skill, and introducing an HTTP-only ktx mcp daemon so external agents can use KTX as a research-capable context layer. * Refine research-agent MCP tools spec after adversarial review iteration 1 * Refine research-agent MCP tools spec after adversarial review iteration 2 * Refine research-agent MCP tools spec after adversarial review iteration 3 * Refine spec: drop connectionName compat carve-out and ground summary/snippet provenance per kind * feat(daemon): validate read-only SQL with sqlglot * feat(context): expose read-only SQL validation port * feat(context): register MCP sql execution tool * feat(context): execute MCP SQL through validated connector path * test(context): update SQL analysis port fixtures * docs: add research-agent MCP sql execution foundation plan * feat(context): add scan-backed entity details service * feat(context): register MCP entity details tool * feat(context): expose local MCP entity details * test(context): align entity details scan fixtures * docs: add research-agent MCP entity_details plan * feat(context): add dictionary search service * feat(context): register MCP dictionary search tool * feat(context): expose local MCP dictionary search * docs: add research-agent MCP dictionary_search plan * feat: add MCP discover data service * feat: expose discover data MCP tool * feat: wire local discover data MCP port * docs: add research-agent MCP discover_data plan * feat(cli): add mcp http security helpers * feat(cli): host mcp over streamable http * feat(cli): manage mcp daemon lifecycle * feat(cli): add ktx mcp commands * fix(cli): stabilize mcp daemon verification * docs: add research-agent MCP http daemon plan * feat(cli): install KTX research skill * feat(cli): configure MCP clients in setup agents * feat(cli): support Claude local MCP setup scope * docs: add research-agent MCP setup-agents plan * refactor(context): use connectionId in warehouse verification tools * docs(context): update ingest verification prompts for connectionId * docs: add research-agent MCP ingest contract convergence plan * chore: build runtime artifacts in conductor setup --------- Co-authored-by: Andrey Avtomonov <7889985+andreybavt@users.noreply.github.com>
2026-05-15 02:35:09 +02:00
describe('normalizeHostHeader', () => {
it('normalizes host headers before allow-list comparison', () => {
expect(normalizeHostHeader('LOCALHOST:7878')).toBe('localhost');
expect(normalizeHostHeader('127.0.0.1:7878')).toBe('127.0.0.1');
expect(normalizeHostHeader('[::1]:7878')).toBe('::1');
expect(normalizeHostHeader(' Example.COM ')).toBe('example.com');
});
});
describe('buildMcpSecurityConfig', () => {
it('allows loopback hosts without a token', () => {
const config = buildMcpSecurityConfig({
host: '127.0.0.1',
port: 7878,
token: undefined,
allowedHosts: [],
allowedOrigins: [],
});
expect(config.token).toBeUndefined();
expect(config.allowedHosts).toEqual(['localhost', '127.0.0.1', '::1']);
});
it('requires a token for non-loopback binding', () => {
expect(() =>
buildMcpSecurityConfig({
host: '0.0.0.0',
port: 7878,
token: undefined,
allowedHosts: [],
allowedOrigins: [],
}),
).toThrow('Binding KTX MCP to 0.0.0.0 requires --token or KTX_MCP_TOKEN');
});
it('validates allowed origins as full origins', () => {
expect(() =>
buildMcpSecurityConfig({
host: '127.0.0.1',
port: 7878,
token: undefined,
allowedHosts: [],
allowedOrigins: ['localhost:7878'],
}),
).toThrow('Allowed origin must be a full origin URL');
});
});
describe('isMcpRequestAuthorized', () => {
const config = buildMcpSecurityConfig({
host: '0.0.0.0',
port: 7878,
token: 'secret-token',
allowedHosts: ['mcp.example.test'],
allowedOrigins: ['https://mcp.example.test'],
});
it('accepts a valid host, origin, and bearer token', () => {
expect(
isMcpRequestAuthorized(
{
path: '/mcp',
headers: {
host: 'mcp.example.test:7878',
origin: 'https://mcp.example.test',
authorization: 'Bearer secret-token',
},
},
config,
),
).toEqual({ ok: true });
});
it('rejects bad host headers before MCP handling', () => {
expect(
isMcpRequestAuthorized(
{ path: '/health', headers: { host: 'evil.example.test' } },
config,
),
).toEqual({ ok: false, status: 403, message: 'Host header is not allowed for KTX MCP.' });
});
it('rejects browser origins unless explicitly allowed', () => {
expect(
isMcpRequestAuthorized(
{
path: '/health',
headers: { host: 'mcp.example.test', origin: 'https://evil.example.test' },
},
config,
),
).toEqual({ ok: false, status: 403, message: 'Origin header is not allowed for KTX MCP.' });
});
it('requires bearer auth on /mcp when token auth is enabled', () => {
expect(
isMcpRequestAuthorized(
{ path: '/mcp', headers: { host: 'mcp.example.test', authorization: 'Bearer wrong' } },
config,
),
).toEqual({ ok: false, status: 401, message: 'Missing or invalid KTX MCP bearer token.' });
});
it('does not require bearer auth on /health', () => {
expect(isMcpRequestAuthorized({ path: '/health', headers: { host: 'mcp.example.test' } }, config)).toEqual({
ok: true,
});
});
});
function postJson(port: number, path: string, body: unknown, headers: Record<string, string> = {}) {
return new Promise<{ status: number; headers: Record<string, string | string[] | undefined>; body: string }>(
(resolve, reject) => {
const payload = JSON.stringify(body);
const req = request(
{
host: '127.0.0.1',
port,
path,
method: 'POST',
headers: {
host: `127.0.0.1:${port}`,
accept: 'application/json, text/event-stream',
'content-type': 'application/json',
'content-length': Buffer.byteLength(payload),
...headers,
},
},
(res) => {
const chunks: Buffer[] = [];
res.on('data', (chunk: Buffer) => chunks.push(chunk));
res.on('end', () =>
resolve({
status: res.statusCode ?? 0,
headers: res.headers,
body: Buffer.concat(chunks).toString('utf8'),
}),
);
},
);
req.on('error', reject);
req.end(payload);
},
);
}
function get(port: number, path: string, headers: Record<string, string> = {}) {
return new Promise<{ status: number; headers: Record<string, string | string[] | undefined>; body: string }>(
(resolve, reject) => {
const req = request(
{
host: '127.0.0.1',
port,
path,
method: 'GET',
headers: { host: `127.0.0.1:${port}`, ...headers },
},
(res) => {
const chunks: Buffer[] = [];
res.on('data', (chunk: Buffer) => chunks.push(chunk));
res.on('end', () =>
resolve({
status: res.statusCode ?? 0,
headers: res.headers,
body: Buffer.concat(chunks).toString('utf8'),
}),
);
},
);
req.on('error', reject);
req.end();
},
);
}
function createTestMcpServer() {
return () => {
const server = new McpServer({ name: 'ktx-test', version: '0.0.0-test' });
server.registerTool('ping', { inputSchema: {} }, async () => ({
content: [{ type: 'text', text: 'pong' }],
}));
return server;
};
}
describe('runKtxMcpHttpServer', () => {
it('serves /health with project metadata', async () => {
const handle = await runKtxMcpHttpServer({
projectDir: '/tmp/ktx-project',
host: '127.0.0.1',
port: 0,
allowedHosts: [],
allowedOrigins: [],
createMcpServer: createTestMcpServer(),
});
try {
const port = (handle.server.address() as AddressInfo).port;
const response = await get(port, '/health');
expect(response.status).toBe(200);
expect(JSON.parse(response.body)).toEqual({
status: 'ok',
projectDir: '/tmp/ktx-project',
port,
});
} finally {
await handle.close();
}
});
it('allocates a stateful MCP session on initialize', async () => {
const handle = await runKtxMcpHttpServer({
projectDir: '/tmp/ktx-project',
host: '127.0.0.1',
port: 0,
allowedHosts: [],
allowedOrigins: [],
createMcpServer: createTestMcpServer(),
});
try {
const port = (handle.server.address() as AddressInfo).port;
const response = await postJson(port, '/mcp', {
jsonrpc: '2.0',
id: 1,
method: 'initialize',
params: {
protocolVersion: '2025-06-18',
capabilities: {},
clientInfo: { name: 'vitest', version: '0.0.0' },
},
});
expect(response.status).toBe(200);
expect(response.headers['mcp-session-id']).toBeTruthy();
} finally {
await handle.close();
}
});
it('rejects unknown session ids with 404', async () => {
const handle = await runKtxMcpHttpServer({
projectDir: '/tmp/ktx-project',
host: '127.0.0.1',
port: 0,
allowedHosts: [],
allowedOrigins: [],
createMcpServer: createTestMcpServer(),
});
try {
const port = (handle.server.address() as AddressInfo).port;
const response = await postJson(
port,
'/mcp',
{ jsonrpc: '2.0', id: 2, method: 'tools/list', params: {} },
{ 'mcp-session-id': 'missing-session' },
);
expect(response.status).toBe(404);
expect(response.body).toContain('Unknown MCP session');
} finally {
await handle.close();
}
});
});