Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Conventions MCP

NPM · CONVENTIONS-MCP · SCANNED SEP 21

Memory for coding conventions and standing instructions that persists across sessions.

Available components

0 this week 84 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security89
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects sharp 0.34.5, reached via @huggingface/transformers > sharp. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 74 of 210 dependencies flagged as unhealthy (2 deprecated). View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to FedgeNo/conventions-mcp). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 3 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability66
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1616 tokens (~230/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management69
  • Stability check failed: the tool surface changed between 3.0.1 and 3.1.1: 0 tool removals, 3 breaking changes, 0 additions. See how to fix → Fail
Tool Coverage95
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 85% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_thought" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Conventions MCP server?

Conventions MCP runs locally as an npm package, launched with npx -y conventions-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · conventions-mcp

# add to Claude Code
claude mcp add fedgeno-conventions-mcp -- npx -y conventions-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "fedgeno-conventions-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "conventions-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "fedgeno-conventions-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "conventions-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add fedgeno-conventions-mcp -- npx -y conventions-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fedgeno-conventions-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "conventions-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add fedgeno-conventions-mcp --command npx --arg -y --arg conventions-mcp
# ~/.hermes/config.yaml
mcp_servers:
  fedgeno-conventions-mcp:
    command: "npx"
    args: ["-y", "conventions-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "fedgeno-conventions-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "conventions-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add fedgeno-conventions-mcp -t stdio -c npx -a -y conventions-mcp
// mcp.json
{
  "mcpServers": {
    "fedgeno-conventions-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "conventions-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 62 to 65.

  • 18 Sept 26 −3

    No change was recorded against any check on this day. Stability & Change Management went from 79 to 59.

  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 75 to 79.

  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 69 to 72.

  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 62 to 65.

  • 11 Sept 26 −2
    • Security disclosure: fail → pass functional
    • Package version: 3.0.1 → 3.1.1 functional
  • 9 Sept 26 +16
    • GHSA-rgj7-g3m4-5g8c affects this package: high security
    • Malware scan: unverified → pass security
  • 8 Sept 26 −8
    • Malware scan: pass → unverified security
    • Stability: 0.90 → fail security
    • Provenance: fail → pass security
    • The attested source repository moved: FedgeNo/conventions-mcp security
    • Schema quality: 191 → 230 functional
    • Package version: 3.0.1 → 3.1.1 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Sept 2026 · Analysed npm/conventions-mcp@3.1.1

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo FedgeNo/conventions-mcp
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/FedgeNo/conventions-mcp/.github/workflows/publish.yml@refs/heads/main
Rekor log index 2753970076
Predicate type https://slsa.dev/provenance/v1
Subject digest sha512:e80fc5bc2b38e6c3c89b0221dff29d6198c48ad775fdef47133eae5ea929d1117a535f11232da4706baf27fdabb0c6168ca9b74daececf2ace72d8765

Background: How many MCP packages publish verified provenance →

Vulnerabilities 2 findings
ID CVE Severity Vector Fix available
GHSA-f88m-g3jw-g9cj high yes
GHSA-rgj7-g3m4-5g8c high yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 210 packages
Packages resolved 210
Deprecated 2
Stale 73
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 7 exposed · ~1,526 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
capture_thought ~605

Save only a durable coding convention, standing instruction, correction, or workflow preference that should govern future sessions or repeated work — e.g. style rules ('always use 2-space indent') or standing directives ('never force-push to main'). Never capture directions specific to the current task, temporary decisions, current status, incident history, commands used for one job, or descriptions of how an individual job was completed; those belong only in the conversation. A preference mentioned while directing one task is not durable unless the user clearly states or confirms that it should apply in the future. Condense each durable rule to one sentence, two if absolutely necessary — no incident stories, user quotes, or example code. Call this when the user establishes or corrects a durable rule, or explicitly asks to retain a genuinely long-lived convention. Classify it yourself using the type/topics/projectScoped fields below, based on the conversation the thought came from. If a single message states multiple distinct durable rules, call this once per rule — don't merge them into one capture — and relay each one individually the same as a single capture, not summarized together. After every successful call, state the captured content verbatim and its project back to the user (the response text already contains both) — this is how they catch a misinterpreted rule and correct or delete it immediately, rather than discovering it wrong much later. Call shape — four top-level arguments, not one wrapped/stringified object: {"content": "Never assign innerHTML; build with DOM methods.", "type": "convention", "topics": ["dom", "security"], "projectScoped": false}

NameTypeReqDescription
contentstringyesA durable rule for future sessions or repeated work, condensed to one sentence — two only if absolutely necessary. Do not submit task-specific directions, temporary choices, current status, incident…
projectScopedbooleanyesTrue ONLY if this rule is specific to the current project/working directory — false (the default) for anything that applies across projects. When true the server stamps the current project id automat…
topicsarrayyes1-3 short topic tags (e.g. 'git', 'testing', 'naming').
typestringyesClassify using the conversation this durable rule came from: 'convention' — a specific coding style/pattern rule; 'instruction' — a standing directive on how to work/behave; 'correction' — a lasting…

No output schema declared.

No examples provided.

delete_thought ~143

Permanently delete a specific captured thought by its ID. This is destructive and irreversible — no undo, no trash. Only call this when the user explicitly asks to delete, remove, or forget a specific thought. Never call it proactively, as a side effect of another action, or on a guess at which ID they mean — if the ID isn't already known from context, use search_thoughts or list_thoughts first and confirm with the user which one before deleting.

NameTypeReqDescription
idintegeryesThe numeric ID of the thought to delete, as shown in search_thoughts/list_thoughts output (e.g. the '#4' in a result)

No output schema declared.

No examples provided.

list_rules ~94

Retrieve every convention, instruction, correction, and preference that applies right now — everything global plus anything scoped to the current project — in one call. A deterministic direct lookup (no embeddings, no ranking), so it won't miss anything a semantic search_thoughts query might rank low. Prefer this over several search_thoughts calls when you want the full standing rule set at once, e.g. at the start of unfamiliar work.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_thoughts ~29

List all captured conventions/instructions, optionally filtered by type.

NameTypeReqDescription
typestring

No output schema declared.

No examples provided.

search_thoughts ~113

Look up previously stored coding conventions, standing instructions, and preferences, by meaning and by exact keyword match (hybrid search). Call this proactively before starting unfamiliar coding work, or when uncertain about a style/convention choice in a project — don't wait for the user to ask. Also call it when the user references a past preference or rule ('like we discussed', 'the usual way', 'you know how I like it').

NameTypeReqDescription
limitinteger
querystringyesWhat to search for

No output schema declared.

No examples provided.

thought_stats ~29

Get a summary of all captured durable rules: totals, types, top topics, and per-project counts.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

update_thought ~513

Correct or refine an existing thought's content in place — same id, re-embedded and re-tagged from the new content. Condense the rule to one sentence, two if absolutely necessary — no incident stories, user quotes, or example code. Use this instead of delete_thought + capture_thought whenever the user is correcting, refining, or replacing what a specific existing thought says (a stale convention, a preference that's since changed) rather than adding an unrelated new one. If the id isn't already known from context, use search_thoughts or list_thoughts first and confirm with the user which one before updating. Re-classify using the type/topics/projectScoped fields below, based on the corrected content and the conversation it came from. After a successful call, state the updated content verbatim and its project back to the user (the response text already contains both) — this is how they catch a misinterpreted rule and correct or delete it immediately. Call shape — five top-level arguments, not one wrapped/stringified object: {"id": 4, "content": "Never assign innerHTML; build with DOM methods.", "type": "convention", "topics": ["dom", "security"], "projectScoped": false}

NameTypeReqDescription
contentstringyesThe corrected/replacement content — condensed to one sentence, two if absolutely necessary, with no padding from the incident/user's words/example files — same as capture_thought
idintegeryesThe numeric ID of the thought to update, as shown in search_thoughts/list_thoughts output (e.g. the '#4' in a result)
projectScopedbooleanyesTrue ONLY if this rule is specific to the current project/working directory — false (the default) for anything that applies across projects. When true the server stamps the current project id automat…
topicsarrayyes1-3 short topic tags (e.g. 'git', 'testing', 'naming').
typestringyesClassify using the conversation this durable rule came from: 'convention' — a specific coding style/pattern rule; 'instruction' — a standing directive on how to work/behave; 'correction' — a lasting…

No output schema declared.

No examples provided.

Common questions

What is the Conventions MCP server?

Conventions MCP is listed in the public MCP registry as io.github.FedgeNo/conventions-mcp. Memory for coding conventions and standing instructions that persists across sessions. This page covers its npm package (conventions-mcp).

Is the Conventions MCP server safe to use?

Conventions MCP scores 84 out of 100 on VerifyMCP. We recorded 2 known advisories against it as of 21 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Conventions MCP server expose?

Conventions MCP exposes 7 tools: capture_thought, update_thought, delete_thought, search_thoughts, list_thoughts, and 2 more. Their descriptions and schemas cost roughly 1,526 tokens of context every time the server is loaded.

Is the Conventions MCP server still maintained?

Conventions MCP is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Conventions MCP server under?

Conventions MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.