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.

Nudge

PYPI · NUDGE-MCP · SCANNED SEP 20

MCP server that nudges better AI session behavior through token usage and efficiency analysis

Available components

0 this week 63 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 Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 1 of 15 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency6
Schema Quality & AI Usability89
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1789 tokens (~111/item across 16 items; 14 tools + 2 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 Management90
  • Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 14 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the Nudge MCP server?

Nudge runs locally as a PyPI package, launched with uvx nudge-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · nudge-mcp

# add to Claude Code
claude mcp add jwill824-nudge-mcp -- uvx nudge-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "jwill824-nudge-mcp": {
      "command": "uvx",
      "args": [
        "nudge-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "jwill824-nudge-mcp": {
      "command": "uvx",
      "args": [
        "nudge-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add jwill824-nudge-mcp -- uvx nudge-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jwill824-nudge-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "nudge-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add jwill824-nudge-mcp --command uvx --arg nudge-mcp
# ~/.hermes/config.yaml
mcp_servers:
  jwill824-nudge-mcp:
    command: "uvx"
    args: ["nudge-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "jwill824-nudge-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "nudge-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add jwill824-nudge-mcp -t stdio -c uvx -a nudge-mcp
// mcp.json
{
  "mcpServers": {
    "jwill824-nudge-mcp": {
      "command": "uvx",
      "args": [
        "nudge-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 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 16 Sept 26 0
    • Stability: 0.97 → pass security
  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 −14
    • Malware scan: pass → unverified security
  • 12 Sept 26 +15
    • Malware scan: unverified → pass security
  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

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 20 Sept 2026 · Analysed pypi/nudge-mcp@0.2.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 15 packages
Packages resolved 15
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 14 exposed · ~1,731 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
analyze_copilot_session ~96

Analyse a Copilot CLI session for inefficiencies and behavioural anti-patterns. Checks prompt quality (vague/short prompts), tool batching (parallelism), bash overuse vs specialised tools, and memory utilisation. Defaults to the currently active session (inuse lock detected), then falls back to the most recently modified session.

NameTypeReqDescription
session_idFull or partial session UUID. Omit to use the active/latest session.
NameTypeReqDescription
resultstringyes

No examples provided.

claude_calibrate_pricing ~80

Update the pricing discount factor from actual Claude Code billing. Run this each month after your billing statement resets. Provide the actual_billed amount shown on your subscription page.

NameTypeReqDescription
actual_billednumberyesActual amount billed shown in Claude Code subscription (USD)
monthMonth being calibrated (YYYY-MM). Defaults to previous month.
NameTypeReqDescription
resultstringyes

No examples provided.

claude_monthly_summary ~57

Return total token usage and estimated cost for a Claude Code billing month. Shows spend vs your configured monthly budget and remaining runway. Defaults to the current month.

NameTypeReqDescription
monthMonth in YYYY-MM format. Defaults to current month.
NameTypeReqDescription
resultstringyes

No examples provided.

claude_session_report ~102

Show Claude Code session token usage and cost estimates. Filter by last N sessions, today, a specific month (YYYY-MM), or all time. Returns per-session metrics: cache hit %, estimated cost, tokens/turn, duration.

NameTypeReqDescription
lastintegerShow last N sessions (default: 20)
monthFilter to a specific month, e.g. '2026-04'
todaybooleanShow today's sessions only
NameTypeReqDescription
resultstringyes

No examples provided.

claude_tool_impact ~180

Analyze how a specific tool affects Claude Code session efficiency. Scans session history to compare tokens/turn, cache hit %, and cost between sessions that used the tool and those that didn't. Useful for measuring the real-world impact of tools like 'serena', 'ck', 'ast-grep', 'Read', 'Grep', or any MCP/built-in tool. Provide the tool name as you'd refer to it naturally, e.g. 'serena', 'ck', 'ast-grep'.

NameTypeReqDescription
monthLimit analysis to a specific month, e.g. '2026-04'. Defaults to all history.
toolstringyesTool name to analyze. Examples: 'serena', 'ck', 'ast-grep', 'Read', 'Grep', 'Glob', 'Bash'. Case-insensitive.
NameTypeReqDescription
resultstringyes

No examples provided.

configure_subscription ~304

Update the active Claude Code or GitHub Copilot subscription plan and monthly budget. Use this when you change plans or when your admin adjusts your budget. Provide a named plan key and/or a custom monthly_budget override. Claude plans: claude_pro ($20), claude_max_100 ($100), claude_max_200 ($200), claude_max_400 ($400), api ($0). Copilot plans: copilot_free ($0), copilot_pro ($10), copilot_pro_plus ($39), copilot_business ($19/seat), copilot_enterprise ($39/seat). For Copilot Pro, you can also set overage_budget to track the additional premium request budget you've configured on top of your base plan (e.g. overage_budget=25.0 means $10 base + $25 overage cap = $35 total).

NameTypeReqDescription
monthly_budgetCustom monthly budget in USD. Overrides the plan default.
overage_budgetCopilot only. Additional premium request budget cap in USD (e.g. 25.0).
planNamed plan key. Claude: claude_pro, claude_max_100, claude_max_200, claude_max_400, api. Copilot: copilot_free, copilot_pro, copilot_pro_plus, copilot_business, copilot_enterprise.
servicestringyesWhich service to configure: 'claude' or 'copilot'
NameTypeReqDescription
resultstringyes

No examples provided.

copilot_behavior_report ~99

Cross-session pattern analysis for GitHub Copilot CLI sessions. Aggregates behavioural signals across recent sessions to surface recurring inefficiencies: vague prompts, low tool parallelism, bash overuse, missing memory calls. Returns a scored summary with actionable recommendations.

NameTypeReqDescription
lastintegerNumber of recent sessions to analyse (default: 10)
monthLimit to a specific month, e.g. '2026-04'
NameTypeReqDescription
resultstringyes

No examples provided.

copilot_budget_forecast ~105

Forecast end-of-month Copilot spend and estimate savings from fixing inefficiencies. Uses burn rate from recorded spend + session history to project end-of-month cost. Analyses behavioral waste (low batching, bash overuse, vague prompts) and shows how fixing each issue would offset the projected spend. Requires record_copilot_spend and configure_subscription (overage_budget) to be set.

NameTypeReqDescription
monthMonth in YYYY-MM format. Defaults to current month.
NameTypeReqDescription
resultstringyes

No examples provided.

copilot_model_efficiency ~110

Analyse how well the active model matched task complexity across Copilot CLI sessions. Scores each turn 0–8 (prompt length, output tokens, tool count, unique tools), classifies each as over-powered / fit / under-powered, and estimates savings from switching simple turns to a budget model.

NameTypeReqDescription
lastintegerNumber of most-recent sessions to analyse (default: 10)
monthFilter to a specific month, e.g. '2026-04'
NameTypeReqDescription
resultstringyes

No examples provided.

copilot_monthly_summary ~70

Monthly output token summary for GitHub Copilot CLI sessions. Shows total output tokens, session count, top projects, and at-API-rate equivalent cost vs your flat subscription budget. Defaults to the current month.

NameTypeReqDescription
monthMonth in YYYY-MM format. Defaults to current month.
NameTypeReqDescription
resultstringyes

No examples provided.

copilot_premium_usage ~131

Fetch live Copilot premium request usage from the GitHub API. Calls GET /users/{username}/settings/billing/premium_request/usage and shows requests used, cost by model, and progress against your configured overage budget. Uses the gh CLI token automatically; falls back to the GH_TOKEN or GITHUB_TOKEN environment variables. Requires a fine-grained PAT (or gh CLI login) with 'Plan' (read) permission. Only works for individual Copilot plans — not org/enterprise-managed licenses.

NameTypeReqDescription
monthMonth in YYYY-MM format. Defaults to current month.
NameTypeReqDescription
resultstringyes

No examples provided.

copilot_session_report ~134

Show GitHub Copilot CLI session output token usage and efficiency metrics. Reads directly from ~/.copilot/session-state. Filter by last N sessions, today, or a specific month (YYYY-MM). Returns per-session: output tokens, turns, duration, tokens/turn, tools used, model. Note: only output tokens are tracked (Copilot CLI does not expose input/cache token counts).

NameTypeReqDescription
lastintegerShow last N sessions (default: 20)
monthFilter to a specific month, e.g. '2026-04'
todaybooleanShow today's sessions only
NameTypeReqDescription
resultstringyes

No examples provided.

copilot_tool_impact ~154

Analyze how a specific tool affects Copilot CLI session efficiency. Scans Copilot CLI session history to compare output tokens/turn and estimated cost between sessions that used the tool and those that didn't. Useful for measuring the real-world impact of tools like 'serena', 'ck', 'ast-grep', 'view', 'bash', or any MCP tool. Provide the tool name as you'd refer to it naturally, e.g. 'serena', 'ck', 'bash'.

NameTypeReqDescription
monthLimit analysis to a specific month, e.g. '2026-04'. Defaults to all history.
toolstringyesTool name to analyze. Case-insensitive substring match against MCP tool names.
NameTypeReqDescription
resultstringyes

No examples provided.

record_copilot_spend ~109

Record actual Copilot overage spend for a month. Use this when you can see your real spend in the GitHub billing UI but the API isn't accessible (e.g. org/enterprise-managed plans). The recorded amount is shown in copilot_monthly_summary alongside your overage budget cap.

NameTypeReqDescription
amountnumberyesActual overage spend in USD (e.g. 17.72).
monthMonth in YYYY-MM format. Defaults to current month.
NameTypeReqDescription
resultstringyes

No examples provided.

Common questions

What is the Nudge MCP server?

Nudge is an MCP server listed in the public MCP registry as io.github.jwill824/nudge-mcp. MCP server that nudges better AI session behavior through token usage and efficiency analysis. This page covers its PyPI package (nudge-mcp).

Is the Nudge MCP server safe to use?

Nudge scores 63 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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 Nudge MCP server expose?

Nudge exposes 14 tools: claude_session_report, claude_monthly_summary, claude_calibrate_pricing, claude_tool_impact, copilot_tool_impact, and 9 more. Their descriptions and schemas cost roughly 1,731 tokens of context every time the server is loaded.

Is the Nudge MCP server still maintained?

Nudge is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.