Power your agent
Instal dari penerbit. Bukan endpoint PlugMCP.
URL remote atau perintah di mesin Anda? Perbedaan kedua cara instal
Jalankan di PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
BukaDari penerbit
Drift stops an AI agent from writing code that violates conventions your repo already follows. It runs entirely on your machine.
Beta install: build from source. Nothing is published to npm yet —
npm install -g @drift/clidoes not work, and thedriftdetectpackage on npm is the unrelated v1 from January. Building needs a Rust toolchain () because the scan engine is Rust.
Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.
git clone https://github.com/dadbodgeoff/drift.git && cd drift
pnpm install --frozen-lockfile
pnpm build && pnpm build:engine
# There is no `drift` binary yet; the entry point is the built CLI.
alias drift="node $PWD/packages/cli/dist/main.js"
drift doctor --repo-root . # fails loudly if the toolchain is missing
Then, in the repository you want to protect:
cd your-repo
drift start --repo-root . --accept-defaults
start prints whether the convention it accepted will actually block, and the command to make it a
gate if it will not. Now have an agent add a route that queries the database directly, the way a
hundred other routes in your repo do not, and check the change:
drift check --diff HEAD~1...HEAD --scope changed-hunks
It names the file, the line, and the convention that was broken. In block mode it exits 2.
--diff main...HEADonly works once your branch has commits thatmaindoes not. On a freshly cloned repo you are onmain, so that range is empty and Drift refuses rather than reporting a pass it cannot support — exit3. That refusal is correct; give it a range with changes in it.
Drift enforces one convention family well, and says so rather than implying more:
It does not review code generally, support other languages, modify your source, or sync anything to a server.
The data layer is recognised when its import specifier contains prisma, database, db or
data-access. A repo naming its data layer store or supabase must declare it with
--data-modules. Drift bootstraps and enforces a declared layering contract — it does not
learn conventions in general, and the claims manifest blocks that claim explicitly.
Security heuristics exist behind --experimental-security and are not proofs. Their own audit
is in docs/internal/architecture/security-heuristic-audit.md.
Evaluated on seven open-source Next.js repos on every change
(pnpm eval:external):
And, because the number that decides whether a first session is tolerable is not recall but how often
Drift declines to answer — eight ordinary edits per repo, none of them a violation
(pnpm eval:bench):
Every check reports its own coverage, so a clean result is never mistaken for full coverage. Where
Drift cannot resolve something it says so, with the offending specifiers — see
drift doctor and summary.import_coverage.
If findings appear but the check exits 0, the convention is in warn mode, deliberately.
Drift infers the convention from the violations themselves, so a repo where every route touches the database produces the same statement as one where a single route does. Enforcing both identically would reject new code written exactly like its neighbours. Instead the mode follows the evidence: a minority violating means new violations block; a majority violating means it is a refactor goal, and Drift warns until a human decides.
formbricks (1 route of 83) blocks. dub (~323 of 494) warns.
From the repo you want Drift to inspect:
drift doctor --repo-root .
drift start --repo-root . --accept-defaults
drift doctor --repo-root .
The first doctor run is a zero-write readiness check. After start, run it again as the ongoing local health gate: it validates SQLite migration compatibility, repo registration, contract compatibility, scan freshness, audit-chain integrity, and tracked backup artifacts, then prints the next upkeep commands.
start --accept-defaults is explicit onboarding confirmation. It accepts the deterministic default convention, materializes the repo contract, and baselines existing findings so legacy drift does not block the first check. Omit --accept-defaults when you want to review every candidate manually first.
drift start prints the local SQLite path:
export DRIFT_DB=/path/to/drift.sqlite
Then use the printed repo id with the review loop:
drift baseline status --repo <repo_id>
drift version --json
drift capabilities --json
drift conventions list --repo <repo_id> --status candidate --kind api_route_no_direct_data_access --capability deterministic_check --limit 20 --offset 0 --json
drift conventions accepted --repo <repo_id> --kind api_route_no_direct_data_access --capability deterministic_check --limit 20 --offset 0 --json
drift conventions show <candidate_id> --repo <repo_id> --json
drift ask "what should I know before changing this route?" --repo <repo_id> --path apps/web/app/api/users/route.ts --json
drift prepare "add user search endpoint" --repo <repo_id> --path apps/web/app/api/users/route.ts --json
drift repo map --repo <repo_id> --role api_route --json
drift repo map --repo <repo_id> --limit 50 --offset 0 --json
drift prepare "add user search endpoint" --repo <repo_id> --require-fresh --json
drift checks list --repo <repo_id> --limit 20 --offset 0 --json
drift checks run --repo <repo_id> --command "pnpm test" --timeout-ms 120000 --json
drift policy check-context --repo <repo_id> --path apps/web/app/api/users/route.ts --surface cli-preflight --require-fresh --json
drift check --diff main...HEAD --repo <repo_id> --scope changed-hunks
drift findings list --repo <repo_id>
drift findings list --repo <repo_id> --convention <convention_id> --json
drift findings list --repo <repo_id> --path apps/web/app/api/users/route.ts --require-fresh --json
drift findings list --repo <repo_id> --limit 25 --offset 0 --json
drift findings show <finding_id> --repo <repo_id> --require-fresh --json
drift backup create --repo <repo_id> --confirm
drift backup list --repo <repo_id> --json
drift backup list --repo <repo_id> --limit 20 --offset 0 --json
drift backup list --repo <repo_id> --artifact-status missing --json
drift audit list --repo <repo_id>
drift audit verify --repo <repo_id> --json
drift audit list --repo <repo_id> --target-id <repo_id> --limit 20 --offset 0 --json
drift audit list --repo <repo_id> --since 2026-05-10T00:00:00.000Z --until 2026-05-11T00:00:00.000Z
Backup output prints the verify and restore dry-run commands. Backup list, verify, and restore JSON also include compact summaries so setup scripts can see artifact health, checksum status, restore intent, and rescan requirements without parsing prose:
drift backup verify <backup.sqlite> --repo <repo_id> --checksum <sha256>
drift backup verify <backup.sqlite> --repo <repo_id> --checksum <sha256> --require-checksum
drift --db <target.sqlite> restore <backup.sqlite> --repo <repo_id> --checksum <sha256> --dry-run
drift --db <target.sqlite> restore <backup.sqlite> --repo <repo_id> --checksum <sha256> --require-checksum --dry-run
For stricter restore identity checks, pass the expected repo fingerprint:
drift backup verify <backup.sqlite> --repo <repo_id> --expect-repo-fingerprint <fingerprint>
drift --db <target.sqlite> restore <backup.sqlite> --repo <repo_id> --expect-repo-fingerprint <fingerprint> --dry-run
Contract exports can stay on stdout or be written to one approved artifact:
drift contract export --repo <repo_id> --format json --output ./repo-contract.json --confirm
drift contract import ./repo-contract.json --dry-run
drift contract import ./repo-contract.json --checksum <sha256> --dry-run
drift contract import ./repo-contract.json --checksum <sha256> --require-checksum --dry-run
contract show, contract validate, contract export, contract import --dry-run, and MCP get_repo_contract expose a stable contract_fingerprint for compatibility checks. The fingerprint is computed from canonical contract content, so unordered governance lists do not create false drift.
scan status, prepare, MCP get_scan_status, and MCP get_task_preflight expose a stable scan_fingerprint for the indexed graph plus no-approval governance metadata, summary counts, indexed_file_count, source_change_count, audit integrity, and next commands. Agents can compare the fingerprint before acting and after rescans without reading source code.
ask, prepare, and MCP get_task_preflight can target a specific repo-relative --path, which pins that file into the preflight packet with a requested path reason. Agent-facing context commands also support --require-fresh / require_fresh; when set, Drift refuses stale scan context and tells the agent which drift scan command to run. repo map and MCP get_repo_map include per-file impact annotations for matching conventions, risky areas, and open findings, plus an impact_summary.
policy check-context and MCP get_allowed_context are the path-level gate for agent context access. They return the policy decision, no-approval governance metadata, summary counts, next commands, freshness requirement, scan status, redaction caps, and indexed file impact metadata without reading or emitting source snippets.
findings list --path, findings list --convention, findings list --limit --offset, findings show, and MCP get_findings({ path, convention_id, limit, offset }) give agents and humans bounded review queues plus a drill-down view for one finding. Add --require-fresh / require_fresh when stale findings should be refused before an agent acts.
conventions list --kind --capability --limit --offset keeps the human approval queue bounded and machine-checkable. Use it to separate deterministic blocking candidates from heuristic briefing candidates before accepting anything into the repo contract.
ask, repo map, and MCP get_repo_map are deterministic local context surfaces. They answer from approved contracts, findings, file roles, imports, exports, calls, scan metadata, and policy state; they do not call an LLM, do not mutate Drift state, and do not include source snippets. repo map and MCP get_repo_map support limit/offset pagination so large repo maps stay scriptable.
audit verify --json and MCP get_audit_status check the local audit hash chain and report summary counts, next commands, and the current head hash. Backup verification and restore dry-runs also validate the audit chain and expose summary fields for schema support, checksum checks, artifact size, write intent, and stale-graph rescan guidance.
audit list --target-id --limit --offset keeps governance timelines scriptable as local state grows. Audit events are returned in deterministic created-time order, with total, filtered, returned, and next-offset metadata.
doctor --json includes the same production-state signals in one automation-friendly payload: applied migrations, unsupported/missing migrations, contract schema/fingerprint, scan staleness, audit integrity, backup count, backup artifact problems, and next_commands for initialized repos.
Drift stores product state in SQLite, not a folder full of JSON files.
The database owns:
JSON is only an interface format for CLI automation, MCP responses, contract import/export, and tests.
Commands that do not require governance approval:
drift doctor
drift scan
drift scan status
drift prepare
drift check
drift findings list
drift audit list
Some of these commands write local Drift state, such as scan, start, and check. The important boundary is that they do not mutate source code or approve governance decisions.
Governance changes require explicit human intent:
drift conventions accept <candidate_id> --confirm
drift conventions reject <candidate_id> --reason "..." --confirm
drift conventions edit <candidate_id> --statement "..." --confirm
drift conventions exception add <convention_id> --path <glob> --reason "..." --confirm
drift findings mark-fixed <finding_id> --evidence <file:line> --confirm
drift findings mark-needs-review <finding_id> --reason "..." --confirm
drift findings suppress <finding_id> --reason "..." --confirm
drift findings accept-drift <finding_id> --reason "..." --confirm
drift findings mark-false-positive <finding_id> --reason "..." --confirm
drift baseline create --from main --confirm
drift baseline clear --convention <convention_id> --confirm
drift policy set-egress ... --confirm
drift policy agent grant ... --confirm
drift policy agent revoke ... --confirm
drift contract export ... --confirm
drift contract import <path> --confirm
drift contract waiver add ... --confirm
drift contract waiver remove ... --confirm
drift backup create --confirm
drift restore <backup.sqlite> --confirm
Rust owns the bounded-memory scanning and rule-critical engine pieces.
TypeScript owns the CLI, MCP server, SQLite storage boundary, policy enforcement, onboarding, and packaging.
The product boundary is intentionally CLI-first. The desktop UI comes after the CLI review loop is stable.
Drift does not mutate source code. It stores repo intelligence locally, guides humans and agents with evidence, and requires explicit human confirmation for governance changes.
Use drift capabilities --json or MCP get_capabilities to discover the supported command surface, no-approval agent tools, human-confirmed governance mutations, and deferred surfaces.
The e2e suite packs and installs the workspace packages into a clean consumer project, then runs:
drift doctordrift scandrift conventions list --kind --capability --limit --offsetdrift conventions accepted --kind --capability --limit --offsetdrift start --accept-defaultsdrift scan statusdrift askdrift preparedrift repo mapdrift repo map --limit --offsetdrift checks list --limit --offsetdrift checks rundrift baseline statusdrift contract showdrift checkdrift findings listdrift findings list --conventiondrift findings list --limit --offsetdrift findings list --path --require-freshdrift findings showdrift findings mark-needs-review --confirmdrift findings mark-fixed --confirmdrift audit listdrift audit list --target-id --limit --offsetdrift audit verifydrift backup create --confirmdrift backup listdrift backup list --artifact-status --limit --offsetdrift backup verifydrift restore --dry-rundrift restore --confirmdrift version --jsondrift capabilities --jsonget_runtime_infoget_capabilitiesget_audit_statusget_scan_statusget_repo_contractget_repo_mapget_task_preflightget_conventionsget_findingsget_required_check_executionsget_allowed_contextdrift-mcppnpm beta:proofRun the full gate:
pnpm verify:full
verify:full is two gates. pnpm verify:ci is the half a hosted runner can execute and is what
GitHub Actions runs on every PR. pnpm verify:evals is the external-repo battery — it requires the
seven pinned evaluation repos cloned locally and is not run by CI.
pnpm verify:ci includes pnpm beta:proof, which proves a fresh Rust scan, an accepted contract, a service-delegated route passing, a new direct data-access route blocking, evidence-complete findings, full schema-stable CLI/MCP parity, and audit hash-chain verification.
Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.
Tool
Belum ada daftar tool. Server remote mendapatkannya setelah pemeriksaan kesehatan pertama.
FAQ
Salin konfigurasi stdio untuk Cursor, Claude Desktop, Claude Code, atau VS Code di halaman ini. Konfigurasi ini memakai instalasi dari penerbit, bukan proxy PlugMCP.
Tidak ada variabel lingkungan wajib yang tercantum di catatan ini.
Drift berjalan secara lokal melalui stdio.
Terakhir diperiksa 2026-10-26. Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.
