MCP.Market

Loki Mode MCP server

by asklokesh·io.github.asklokesh/loki-mode·v10.9.1·1.1k stars
No reviews yet

Autonomous spec-to-product coding-agent CLI with an MCP server exposing 39 tools over stdio.

B77/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B77/100

full report

Adoption
Established

1.1k stars4.8k downloads/wk

Reviews

Write one

Nobody has reviewed Loki Mode yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Loki Mode tools (41, 5 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • _env
  • _to_threadwrite action

    Run a blocking callable off the event loop.

  • loki_agent_metrics

    Get agent metrics including token usage, task completion rates, and timing.

  • loki_checkpoint_restore

    List available checkpoints or restore project state from a specific checkpoint.

  • loki_code_search

    Search the loki-mode codebase semantically.

  • loki_code_search_stats

    Get statistics about the code search index.

  • loki_complete_task

    Declare that the current PRD / task is complete.

  • loki_consolidate_memorywrite action

    Run memory consolidation to extract patterns from recent episodes.

  • loki_counter_evidence_template

    Generate a counter-evidence file template for the given iteration.

  • loki_findings

    Read structured code-review findings for a given iteration.

  • loki_get_co_changes

    Find files that frequently change together with a given file.

  • loki_get_doc_coverage

    Get documentation coverage status for the project.

  • loki_get_hotspots

    Get the most frequently changed files in the repository.

  • loki_graph_query

    Answer a codebase question from a knowledge graph instead of reading files.

  • loki_learnings

    Read recent learnings (newest first) from relevant-learnings.json.

  • loki_memory_capture_session_summary

    v7.7.18 capture wedge: store an episode for the current agent session.

  • loki_memory_redact

    Redact memory versions in the managed-agents store whose content matches a regex.

  • loki_memory_retrieve
  • loki_memory_store_pattern

    Store a new semantic pattern learned during this session.

  • loki_metrics_efficiency

    Get efficiency metrics for the current session.

  • loki_project_status

    Get the current project status including RARV cycle state, agent activity, and task progress.

  • loki_quality_report

    Get quality gate results including blind review scores, council verdicts, and test coverage.

  • loki_start_project

    Start a new Loki Mode project from a PRD.

  • loki_state_get

    Get the current Loki Mode state including phase, metrics, and status.

  • loki_task_queue_add

    Add a new task to the Loki Mode task queue.

  • loki_task_queue_list

    List all tasks in the Loki Mode task queue.

  • loki_task_queue_updatewrite action

    Update a task's status or priority.

  • loki_v10_runwrite action

    Start a Loki 10 run in the background (same engine as `loki <ref>`).

  • loki_v10_status

    Read the state of a Loki 10 run from its events log.

  • loki_v10_verifywrite action

    Run `loki verify` on a receipt (or the newest run of a repo).

  • loki_verify_fast

    Verify code deterministically in milliseconds. No model call, no network.

  • lsp_check_exists

    Cheap existence check for a symbol in the current workspace.

  • lsp_find_definition_by_name

    Find where a named symbol is defined, without needing a file position upfront. Convenience wrapper: runs workspace/symbol then returns the first result's location.

  • lsp_find_references

    Find references to the symbol at the given file / line / character.

  • lsp_get_diagnostics

    Return current LSP diagnostics (errors + warnings) for a file.

  • lsp_go_to_definition

    Resolve the definition location for the symbol at file / line / character.

  • lsp_symbol_at_position

    Return the hover / symbol info at the given file / line / character. Uses LSP `textDocument/hover` which returns a `MarkupContent` plus an optional range.

  • lsp_workspace_symbols

    Fuzzy-search symbols across the entire workspace.

  • mem_get

    Fetch full details for one or more memory entries by ID.

  • mem_search

    Search memory using full-text search (FTS5).

  • mem_timeline

    Get chronological context from memory timeline.

Public scan report

scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it

2 medium
  • Code scan555 source files scanned15/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (2)

  • mediumsubprocess with shell=Trueexec.shell-true
    autonomy/lib/workspace.py: …etup: s = subprocess.run(setup, shell=True, cwd=dest, capture_output=True, text=Tr…
  • mediumeval / new Function usedexec.eval
    autonomy/run.sh: … # v7.5.8: Strict whitelist before eval (mirrors app-runner.sh # …
Overall 77/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Loki Mode compares

Against every graded E-commerce MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
77/100
higher than 55% of 2,174 E-commerce servers
Tools
41
the typical E-commerce server has 6
Tools that change things
12%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1,096
more than 95% of 1,047 E-commerce servers
Downloads a week
4,835
more than 95% of 411 E-commerce servers with a package

What its tools let an agent do: 36 read · 5 change

Release history: 2 versions in the registry since 2026-09-14, latest 2026-10-03, typically one every 19 days.

Install Loki Mode in Claude Code, Cursor or VS Code

Runs npx -y loki-mode on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add loki-mode -- npx -y loki-mode
Add to Cursor

What the publisher says

From the Loki Mode repository's README, as published. We do not edit it. Read it on GitHub

Loki Mode

The spec-driven autonomous builder with verified completion.

The free, source-available autonomous coding agent by Autonomi. Same Loki CLI, SDK, and MCP for everyone; the commercial editions for teams and enterprises are sold under the Autonomi brand (Autonomi Cloud, Autonomi Enterprise).

Hand it a spec. It does not accept "done" on an empty diff or failing tests.

Website | Documentation | Installation | Changelog

Install

bun install -g loki-mode          # recommended (npm, Homebrew, Docker below)

Other install methods

Upgrade with loki self-update. Long form: Installation Guide.

Claude Code plugin (adds /loki-grill, /loki-spec-status, /loki-verify)

claude plugin marketplace add asklokesh/loki-mode
claude plugin install loki-mode@loki-mode

Adds three slash commands and the Loki MCP server (memory, task queue, code search, build management) to Claude Code. It calls the CLI rather than bundling it, so install loki-mode above first. Verify with claude plugin list: a healthy install reports Status: enabled.

Use it

loki quickstart                   # guided first build: asks a few questions, quotes cost, builds

That is the whole happy path. It asks for a one-line idea, picks a template, shows the real cost and time estimate before spending anything, then builds. Press Enter through every step and you get a sample Todo app.

One command, no prompts (CI, scripts, containers, any shell without a terminal):

loki quickstart "a todo app with user accounts" --yes

Both halves are required with no terminal: an idea (or a path to a PRD file) and an explicit --yes. Given both, Loki picks the top-ranked template automatically, prints the same honest cost and time estimate, and starts the build without asking anything. Missing either half exits 2 with the needs-a-terminal message and writes nothing, so an ambient LOKIAUTOCONFIRM or a stray argument in CI can never start a paid build on its own. Existing files are never overwritten: if prd.md is present the PRD lands at prd-quickstart.md, then numbered suffixes as needed.

Choose an exact shipped starter when the top-ranked match is not the one you want:

loki quickstart --list-templates
loki quickstart --list-templates --json       # schema-v1 automation output
loki quickstart "an internal reporting workspace" --template dashboard --yes

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-09-19restoreC → Bscore 77: eval / new Function used; subprocess with shell=True
  • 2026-09-19restoreD → Cscore 58: Whole environment serialized (possible credential exfil); eval / new Function used; subprocess with shell=True
  • 2026-09-19restoreF → Dscore 54: Whole environment serialized (possible credential exfil); curl | sh in a script; eval / new Function used

Loki Mode: common questions

Is Loki Mode MCP server safe?
Mostly: it is graded B (77/100). Read the Loki Mode safety report
How do I install Loki Mode?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Loki Mode need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Loki Mode maintained?
The last commit was 20 days ago (2026-10-15). The latest release is v10.9.1.
What can I use instead of Loki Mode?
Servers from other publishers that do the same job: Ecommerce Trends MCP server, PostHog MCP Server and New-Term Radar MCP server.
How does Loki Mode compare with other E-commerce MCP servers?
safety score 77/100 (higher than 55% of 2,174 E-commerce servers); tools 41 (the typical E-commerce server has 6); tools that change things 12% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Loki Mode

Same job from other publishers: the closest match first, then the best rated.

  • Ecommerce Trends MCP
    Product and category demand trend volume over time, with growth signals. Free key at trendsmcp.ai
    A
  • PostHog MCP Server
    Official PostHog MCP Server for product analytics, feature flags, experiments, and more.
    A
  • New-Term Radar
    New AI model, product and repo names as they surface, and the search terms behind them, sized.
    B
  • Idea Reality
    Pre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.
    B
  • Stripe
    MCP server integrating with Stripe - tools for customers, products, payments, and more.
    A

More from asklokesh →