mirror of
https://github.com/Sea-Haven-Industries/sh-mcp.git
synced 2026-10-01 01:13:17 +00:00
Some checks are pending
deploy / deploy (push) Waiting to run
* Add shared transport: dispatch, MCP + OpenAPI adapters, local auth
Add the single authoritative tool-execution path (executeTool) plus the two
universal interfaces over it (design.md §2.5, §7.3):
- dispatch.ts: scope enforcement, ajv input validation, rate limiting, finance
egress redaction (redactDeep), and structured audit emission on one path.
- audit.ts / rate-limit.ts: injected AuditLogger + RateLimiter abstractions.
- mcp.ts: low-level MCP Server with scope-filtered tools/list (tool-hiding) and
tools/call routed through executeTool.
- http.ts: Express host mounting /mcp, /openapi.json, POST /tools/:name, /healthz.
- openapi.ts: buildOpenApiDocument wraps the existing path generator into a full
OpenAPI 3.1 document.
- local-auth.ts: LocalAuthProvider (dev bearer tokens) that refuses to construct
outside SH_MCP_ENV=local and enforces audience binding (design.md §3, §6).
* Add in-memory dev clients; make package tool exports lazy
Add an in-memory Client implementation per integration package (seeded fake
data, no network) selected when SH_MCP_ENV=local (build-plan §4). Gmail/calendar/
tasks dev clients partition by ctx.sub; payments/qbo seed sensitive-looking
fields so the redaction egress path has real targets to mask.
Make the eager default-tool exports in tasks/reminders/qbo LAZY (getDefaultTools)
so importing a package barrel no longer constructs an AWS client at module load
(build-plan §7 'no I/O at import time') — the previous eager construction broke
server startup. Fix payments tsconfig rootDir (src, was '.') so its declarations
resolve under dist/index.d.ts like the other 8 packages.
* Add runnable sh-mcp-ops and sh-mcp-finance servers
Two thin composition-root servers over the shared transport (design.md §3):
- ops: internal-data, knowledge-base, google-maps, gmail, calendar, tasks,
reminders. finance: qbo, payments (audited + redacted on egress).
- config from env only (no hardcoded ids/issuer/tables); SH_MCP_ENV selects
LocalAuthProvider + dev clients (local) vs CognitoAuthProvider + real stubs
(aws). Finance applies the 15-min finance-token TTL ceiling (design.md §2.5).
- index.ts is the only place .listen() is called; a Lambda handler placeholder
is exported but not depended on.
- synth-only CDK stubs (no real IAM/Cognito/WAF) so 'cdk synth' has a valid app
(build-plan §6); READMEs document local run, dev tokens, curl, MCP Inspector.
* Add security-weighted test suite + coverage gate; wire tooling
Add tests for the highest-risk surface (build-plan §5, design.md §7.3):
tool-hiding, server-side scope enforcement (incl. forced hidden calls),
audience binding, input-schema validation, finance redaction on egress, audit
emission with hashed args, prompt-injection regression (tool output is data),
rate limiting, MCP conformance (in-memory transport round-trip), OpenAPI 3.1
validity, and local-auth safety. Add HTTP integration tests (supertest) for both
servers and per-package dev-client tests. 405 tests pass.
Wire the coverage gate into vitest.config.ts: 80% overall, with per-file
thresholds on the auth + dispatch crown jewels; exclude deferred real client
stubs, entrypoints, cdk apps, and aws-only config from the gate (documented).
Extend eslint flat config + add .prettierignore to cover servers/. Commit the
updated package-lock.json.
* Suppress pre-existing dev-tooling + out-of-scope scanner findings
Add written-justification suppressions for the 4 confirmed crit/high pre-push
scanner findings, none of which are in this PR's Phase 1 production code:
- npmaudit vitest / @vitest/coverage-v8 / vite: dev/test-only deps that never
run in the deployed server/Lambda runtime (pins carried from Phase 0b;
Dependabot will bump).
- gitleaks docs/agentforce-plan.md secret: that file is not on this branch and
not in this changeset; flagged for the maintainer to scrub on its own branch.
The deep agentic /sh-security-review (required for this auth/authz-touching PR)
was NOT run by the agent and is flagged outstanding in the PR body.
* Address CodeQL findings: bound ajv error work + edge rate limiting
GHAS code-scanning alerts on this PR:
- dispatch.ts (js/resource-exhaustion): ajv ran with allErrors:true on
untrusted input, letting a crafted payload force unbounded error
enumeration. Switch to allErrors:false (default) so validation
short-circuits on the first failure; the 400 still names that path.
- http.ts (js/missing-rate-limiting): the authenticated routes (/mcp,
/tools/:name) had no edge throttle — auth/JWT verification ran on every
request before the per-sub dispatch limiter could apply. Add an IP-keyed
express-rate-limit in front of authenticate (120/60s default, configurable),
returning the standard 429 shape. Defense-in-depth over the per-sub +
per-tool limiter in executeTool; API GW/WAF remains the production edge.
Tests: +2 cases proving the edge limiter throttles before auth (429, not
401) on /tools and /mcp. 407 pass; tsc/eslint/prettier clean.
* Fix polynomial ReDoS in Bearer-token extraction (CodeQL js/polynomial-redos)
extractBearerToken matched /^Bearer\s+(.+)$/ — \s and . both match a space,
so the two quantifiers overlap and a crafted header can drive polynomial
backtracking. Require the capture to start with a non-whitespace char
(/^Bearer\s+(\S.*)$/), removing the ambiguity → linear match. Behavior is
unchanged for real tokens; +2 regression tests.
* Harden auth + finance redaction (sh-security-review confirmed mediums)
Two confirmed medium findings from the agentic security review:
- Fail-open SH_MCP_ENV: config defaulted to 'local' when the var was unset,
so a deploy that forgot SH_MCP_ENV=aws would silently run LocalAuthProvider
and accept static dev bearer tokens (dev-finance-admin -> finance:admin).
Now fail-closed: SH_MCP_ENV must be explicitly 'local' or 'aws' or the
server refuses to start. Plus an independent guard in LocalAuthProvider
that refuses to construct in an AWS runtime (AWS_LAMBDA_FUNCTION_NAME /
AWS_EXECUTION_ENV present), regardless of the env flag.
- Finance egress redaction gap: redactDeep only wholesale-masked a sensitive
key when its value was a scalar; an object/array under a sensitive key was
recursed into, letting a bare nested value (e.g. {account:{number:...}})
escape the keyword-gated pattern matcher. Now the entire subtree under a
sensitive key is masked. No current finance tool emitted such shapes (all
flat strings), so this closes a latent hole in the universal safety net.
+4 tests (subtree redaction, AWS-runtime guard). 411 pass; coverage gate green.
Review also produced lows (memo free-text digits, unsalted argsHash,
unauth /openapi.json by-design, session-cap no-reset by-design) tracked
separately; 0 confirmed critical/high — review verdict PASS.
155 lines
5.6 KiB
TypeScript
155 lines
5.6 KiB
TypeScript
/**
|
|
* Knowledge-base client interface.
|
|
*
|
|
* The production implementation calls Amazon Bedrock Knowledge Base Retrieve API.
|
|
* Swap the implementation by injecting a different KnowledgeBaseClient at the call
|
|
* site — tests pass a mock, production code uses BedrockKnowledgeBaseClient.
|
|
*
|
|
* Future note: when migrating to Salesforce Data Cloud, replace
|
|
* BedrockKnowledgeBaseClient with a DataCloudKnowledgeBaseClient that satisfies
|
|
* the same KnowledgeBaseClient interface.
|
|
*/
|
|
|
|
/** A single retrieval result returned by the knowledge base. */
|
|
export interface KnowledgeBaseResult {
|
|
/** Source document URI or human-readable reference (e.g. S3 URI, Notion page title). */
|
|
source: string;
|
|
/** Relevance score in the range [0, 1] as returned by the underlying retriever. */
|
|
score: number;
|
|
/** Text passage extracted from the source document. */
|
|
passage: string;
|
|
}
|
|
|
|
/** Options forwarded to the underlying retriever on each query. */
|
|
export interface RetrieveOptions {
|
|
/** Free-text query string. */
|
|
query: string;
|
|
/**
|
|
* Maximum number of results to return.
|
|
* Defaults to 5 if omitted; callers should not exceed 20.
|
|
*/
|
|
maxResults?: number;
|
|
}
|
|
|
|
/**
|
|
* The interface every knowledge-base client must satisfy.
|
|
* Production code uses BedrockKnowledgeBaseClient; tests supply a mock.
|
|
*/
|
|
export interface KnowledgeBaseClient {
|
|
retrieve(options: RetrieveOptions): Promise<KnowledgeBaseResult[]>;
|
|
}
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Production implementation — Bedrock Knowledge Base Retrieve API
|
|
// ---------------------------------------------------------------------------
|
|
|
|
/**
|
|
* Configuration for the production Bedrock KB client.
|
|
* All values come from environment variables; no defaults are hard-coded so
|
|
* that the module can be imported without triggering any AWS calls.
|
|
*/
|
|
export interface BedrockKnowledgeBaseClientConfig {
|
|
/** Bedrock Knowledge Base ID (e.g. "ABCD1234EF"). */
|
|
knowledgeBaseId: string;
|
|
/** AWS region (e.g. "us-east-1"). */
|
|
region: string;
|
|
}
|
|
|
|
/**
|
|
* Production Bedrock KB client.
|
|
*
|
|
* The @aws-sdk/client-bedrock-agent-runtime package is imported LAZILY inside
|
|
* retrieve() so that importing this module at the top level (e.g. in tests)
|
|
* does NOT trigger any network activity or AWS credential resolution.
|
|
*
|
|
* TODO(auth-layer): once the deferred auth layer is in place, thread the
|
|
* caller's AWS credentials / assumed role ARN through here if we want
|
|
* per-user IAM audit trails on Bedrock calls.
|
|
*/
|
|
export class BedrockKnowledgeBaseClient implements KnowledgeBaseClient {
|
|
private readonly config: BedrockKnowledgeBaseClientConfig;
|
|
|
|
constructor(config: BedrockKnowledgeBaseClientConfig) {
|
|
this.config = config;
|
|
}
|
|
|
|
/**
|
|
* Calls the Bedrock Retrieve API.
|
|
*
|
|
* The AWS SDK import is deferred to keep module load side-effect-free.
|
|
* If the environment lacks AWS credentials this will throw at call time,
|
|
* not at import time — which is the desired behaviour for testing.
|
|
*/
|
|
async retrieve(options: RetrieveOptions): Promise<KnowledgeBaseResult[]> {
|
|
// @aws-sdk/client-bedrock-agent-runtime is intentionally absent from package.json
|
|
// until the Lambda runtime bundle is assembled. The module specifier is stored in a
|
|
// variable so TypeScript skips static module resolution at build time.
|
|
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
|
const dynImport = (s: string): Promise<any> =>
|
|
new Function('s', 'return import(s)')(s) as Promise<any>;
|
|
|
|
interface BedrockRetrievalResult {
|
|
location?: { s3Location?: { uri?: string }; type?: string };
|
|
score?: number;
|
|
content?: { text?: string };
|
|
}
|
|
interface BedrockRetrieveResponse {
|
|
retrievalResults?: BedrockRetrievalResult[];
|
|
}
|
|
|
|
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
|
const { BedrockAgentRuntimeClient, RetrieveCommand } = (await dynImport(
|
|
'@aws-sdk/client-bedrock-agent-runtime',
|
|
)) as {
|
|
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
|
BedrockAgentRuntimeClient: new (cfg: { region: string }) => {
|
|
send: (cmd: any) => Promise<BedrockRetrieveResponse>;
|
|
};
|
|
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
|
RetrieveCommand: new (input: any) => unknown;
|
|
};
|
|
|
|
const client = new BedrockAgentRuntimeClient({ region: this.config.region });
|
|
|
|
const command = new RetrieveCommand({
|
|
knowledgeBaseId: this.config.knowledgeBaseId,
|
|
retrievalQuery: { text: options.query },
|
|
retrievalConfiguration: {
|
|
vectorSearchConfiguration: {
|
|
numberOfResults: options.maxResults ?? 5,
|
|
},
|
|
},
|
|
});
|
|
|
|
const response = await client.send(command);
|
|
const rawResults = response.retrievalResults ?? [];
|
|
|
|
return rawResults.map((r: BedrockRetrievalResult) => ({
|
|
source: r.location?.s3Location?.uri ?? r.location?.type ?? 'unknown',
|
|
score: r.score ?? 0,
|
|
passage: r.content?.text ?? '',
|
|
}));
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Build a production BedrockKnowledgeBaseClient from environment variables.
|
|
*
|
|
* Expected env vars:
|
|
* KNOWLEDGE_BASE_ID — Bedrock Knowledge Base ID
|
|
* AWS_REGION — AWS region (falls back to 'us-east-1')
|
|
*
|
|
* This factory is intentionally NOT called at module import time.
|
|
*/
|
|
export function createBedrockClientFromEnv(): BedrockKnowledgeBaseClient {
|
|
const knowledgeBaseId = process.env['KNOWLEDGE_BASE_ID'];
|
|
if (!knowledgeBaseId) {
|
|
throw new Error(
|
|
'KNOWLEDGE_BASE_ID environment variable is required for the production KB client',
|
|
);
|
|
}
|
|
return new BedrockKnowledgeBaseClient({
|
|
knowledgeBaseId,
|
|
region: process.env['AWS_REGION'] ?? 'us-east-1',
|
|
});
|
|
}
|