sh-mcp/servers/sh-mcp-ops/README.md
Adam Moussa 22c09e99fe
Some checks are pending
deploy / deploy (push) Waiting to run
Phase 1: runnable MCP + OpenAPI servers (ops + finance) (#3)
* 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.
2026-06-26 13:33:21 -04:00

97 lines
4.4 KiB
Markdown

# sh-mcp-ops
Operations-tier Sea Haven MCP server. Exposes the **ops** tool registry
(internal-data, knowledge-base, google-maps, gmail, calendar, tasks, reminders —
see `docs/design.md §3`) over **two universal interfaces backed by one shared
dispatch path**:
- **MCP** (Streamable HTTP) at `POST /mcp` — via `@modelcontextprotocol/sdk`.
- **OpenAPI 3.1** — full document at `GET /openapi.json`, plus one
`POST /tools/{tool-name}` endpoint per tool.
All scope enforcement, audience binding, input validation, rate limiting, and
audit logging live in `@sh-mcp/shared` (`executeTool`) and are identical across
both interfaces (`docs/design.md §2.5`).
## Run locally (no AWS, no Cognito)
```bash
# from the repo root
npm install
npm run build # or: npx tsc -b
SH_MCP_ENV=local PORT=8081 npm run start -w @sh-mcp/server-ops
# or live-reload: SH_MCP_ENV=local npm run dev -w @sh-mcp/server-ops
```
`SH_MCP_ENV=local` wires **in-memory dev clients** (seeded fake data, no network)
and the `LocalAuthProvider`, which maps dev bearer tokens to identities. The
local provider refuses to construct unless `SH_MCP_ENV=local`.
### Endpoints
| Method | Path | Auth | Notes |
| ------ | -------------------- | ---- | -------------------------------------- |
| GET | `/healthz` | no | `{ "status": "ok" }` |
| GET | `/openapi.json` | no | full OpenAPI 3.1 document |
| POST | `/mcp` (+GET/DELETE) | yes | MCP Streamable HTTP |
| POST | `/tools/:name` | yes | one-shot tool call, JSON in / JSON out |
### Dev bearer tokens (local only)
| Token | Identity | Scopes |
| --------------- | ------------------------ | -------------------------------------------- |
| `dev-ops-only` | ops-only@seahavenind.com | `ops:read`, `ops:tasks` |
| `dev-assistant` | lauren@seahavenind.com | + `gmail:self`, `calendar:self` |
| `dev-ops-admin` | adam@seahavenind.com | `ops:read`, `ops:tasks`, gmail/calendar self |
Tokens minted for a different tier (e.g. `dev-finance`) are **rejected** by this
server (audience binding).
### Sample curl
```bash
TOKEN=dev-ops-only
curl -s localhost:8081/healthz
curl -s localhost:8081/openapi.json | jq '.openapi, (.paths | keys | length)'
curl -s -X POST localhost:8081/tools/lookup_work_order \
-H "Authorization: Bearer $TOKEN" -H 'Content-Type: application/json' \
-d '{"workOrderId":"WO-1001"}' | jq
# tool-hiding is convenience; the boundary is server-side — a forced call to a
# tool you lack scope for is still 403:
curl -s -o /dev/null -w '%{http_code}\n' -X POST localhost:8081/tools/search_inbox \
-H "Authorization: Bearer $TOKEN" -H 'Content-Type: application/json' \
-d '{"query":"invoice"}' # → 403 (needs gmail:self)
```
### MCP Inspector
Point the [MCP Inspector](https://github.com/modelcontextprotocol/inspector) at
`http://localhost:8081/mcp` (transport: **Streamable HTTP**) and set an
`Authorization: Bearer dev-assistant` header. `tools/list` reflects only the
tools your token's scopes permit.
## Environment
| Var | Mode | Purpose |
| ---------------------------- | ---- | --------------------------------------------- |
| `SH_MCP_ENV` | both | `local` (dev clients) or `aws` (real/Cognito) |
| `PORT` | both | listen port (default 8081) |
| `AWS_REGION` | aws | Cognito region |
| `COGNITO_USER_POOL_ID` | aws | issuer / JWKS source |
| `COGNITO_ALLOWED_CLIENT_IDS` | aws | comma-list; the audience boundary |
| `GOOGLE_MAPS_API_KEY` | aws | maps client |
| `REMINDER_TARGET_ARN` etc. | aws | scheduler wiring |
`aws` mode is not runtime-exercised in Phase 1 (real external clients are
deferred stubs; Cognito infra is out of scope — see `docs/build-plan-phase-1.md`).
## CDK
`cdk/app.ts` is a **synth-only** placeholder (`npm run synth -w @sh-mcp/server-ops`)
so the CI `cdk synth` gate has a valid app. It provisions **no** real IAM,
Cognito, API Gateway, or WAF — those land in a later phase behind the mandatory
IAM cross-review.