SCYTHE (Siddharthk17/SCYTHE) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 19 tools. No publisher has claimed this listing.

Emerging

74/100

SCYTHE

Item: SCYTHE
Rating: 74
Author: M8ven

Scythe (ctx) is a live, auto-updating codebase context engine. It maintains a local SQLite relational graph of your repository, synced dynamically on edit by AI models, guaranteeing structured, zero-drift context under 10k tokens — even for million-line codebases.

→ Siddharthk17/SCYTHE · listed on github_repo_search

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

Siddharthk17

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

✅

No credential exfiltration, no sensitive file access, no obfuscation

Static analysis found nothing flowing your secrets to unexpected places.

✅

Open source with a license and README

Anyone can audit the code, the license is declared, and the publisher documents what it does.

🔐

You'll be asked for 1 credential: ANTHROPIC_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// tools this server exposes19 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

get_context

Retrieve assembled context for a file: project info, directory tree, dangers, decisions, file summary, dependency summaries, and call graph. Returns a multi-zone document (Zone 3/0/1/2) pruned to fit an 8000-token budget.

get_function

Retrieve the full record for a specific function by its ID, including signature, summary, danger flags, source code, and staleness warnings.

search

Full-text search across file purposes/summaries and function summaries/signatures using FTS5 (or LIKE fallback). Returns ranked matches.

get_dangers

List all recorded danger zones, optionally filtered by file scope. Shows descriptions and reasons.

get_decisions

List recorded architectural decisions, optionally filtered by scope. Shows the decision, rejected alternatives, and rationale.

get_callers

Find all functions that call a given function. Returns caller ID, signature, and file location.

get_tainted

List all functions currently marked as tainted (dependent on changed code). Optionally filter by file.

ctx_status

Overview of the ctx index: file/function counts, staleness, taint queue, last recorded commit, hook status, and MCP configuration presence.

update_file

Update record for an indexed file. Writes semantic metadata (purpose, summary, danger, last_change, system). Resets confidence to 1.0, clears stale flag. Does NOT reindex.

update_function

Update record for an indexed function. Writes summary, summary_long, danger, mutates. Clears taint and stale flags, resets confidence to 1.0. Does NOT reindex.

add_danger

Record a new danger zone. Writes to the dangers table with a deterministic ID. Does NOT reindex.

remove_danger

Remove a danger zone by ID. Only model-added dangers can be removed via MCP. Human-added dangers require the CLI.

add_decision

Record an architectural decision. Writes to the decisions table with a deterministic ID. Does NOT reindex.

log_session

Log a session history entry to the session_log table. Enforces a rolling 10-entry cap. Does NOT reindex.

log_change

Log a change record for a file to the changes table. Sets author='model'. Enforces a rolling 20-per-file cap. Does NOT reindex.

mark_tainted

Mark a specific function as tainted and add it to the taint_queue. Does NOT reindex.

clear_taint

Clear the tainted flag from a function after review. Removes from taint_queue. Does NOT reindex.

update_summary

Update summary for a file or function. Resets confidence to 1.0, clears stale/taint. Does NOT reindex.

plan

Log a development plan to the session history. Does NOT reindex.

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

configGITHUB_BASE_REF

🔐 secretANTHROPIC_API_KEY

configCTX_OLLAMA_HOST

configCTX_EXPLAIN_MODEL

configCTX_LLM_MODEL

configCTX_PR_MODEL

configCTX_REVIEW_MODEL

configCTX_OLLAMA_MODEL

configCTX_WATCH_DEBOUNCE_MS

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

19/19 tools missing one or more hints — get_context (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_function (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +16 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 2 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Score](https://m8ven.ai/badge/mcp/siddharthk17/scythe)](https://m8ven.ai/mcp/siddharthk17/scythe)

Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.

commit: 951cc9520b7bc1855bb311090c442de8dfb24bbd

code hash: e8369b77f2d48adbc9b796c48df2c14eb515d91613c262cf1de0d5ceb6213fdf

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client