# Tidegap (npm · @tidegap/mcp) Runs non-urgent LLM tasks at the cleanest grid hour before a deadline, via Batch APIs when allowed. - Trust score: 88/100 (high trust) - Change this week: +7 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-11-06 ## Components - npm · `@tidegap/mcp`: 88/100 (this document), [markdown](https://verifymcp.io/servers/tidegap-tidegap/tidegap-mcp.md), [page](https://verifymcp.io/servers/tidegap-tidegap/tidegap-mcp) ## Channel facts - Registry: `npm` - Package: `@tidegap/mcp` - Version: `0.20.0` - Transport: `stdio` ## Trust breakdown 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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-11-06. - **Supply Chain Security**: 98/100 - No malware found by supply-chain analysis. - No known CVEs affecting this package version or its production dependencies. - No install/post-install scripts declared. - 51 of 130 dependencies flagged as unhealthy (1 deprecated). - **Provenance & Transparency**: 100/100 - Source repository is publicly reachable at the declared URL. - Cryptographically verified build provenance (signed, bound to tidegap/tidegap). - Clear OSI-approved license (Apache-2.0). - Actively maintained (last published 3 days ago). - Publishes a security disclosure policy (SECURITY.md). - **Schema Quality & AI Usability**: 61/100 - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 6107 tokens (~508/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 70/100 - Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### How do I install the Tidegap MCP server? Tidegap runs locally as an npm package, launched with npx -y @tidegap/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add tidegap-tidegap -- npx -y @tidegap/mcp ``` ### Cursor ```json { "mcpServers": { "tidegap-tidegap": { "command": "npx", "args": [ "-y", "@tidegap/mcp" ] } } } ``` ### VS Code ```json { "servers": { "tidegap-tidegap": { "command": "npx", "args": [ "-y", "@tidegap/mcp" ] } } } ``` ### Codex ```bash codex mcp add tidegap-tidegap -- npx -y @tidegap/mcp ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "tidegap-tidegap": { "type": "local", "command": [ "npx", "-y", "@tidegap/mcp" ], "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add tidegap-tidegap --command npx --arg -y --arg @tidegap/mcp ``` ### Hermes ```yaml mcp_servers: tidegap-tidegap: command: "npx" args: ["-y", "@tidegap/mcp"] ``` ### Netclaw ```json { "McpServers": { "tidegap-tidegap": { "Transport": "stdio", "Command": "npx", "Arguments": [ "-y", "@tidegap/mcp" ] } } } ``` ### Vellum ```bash assistant mcp add tidegap-tidegap -t stdio -c npx -a -y @tidegap/mcp ``` ### Other ```json { "mcpServers": { "tidegap-tidegap": { "command": "npx", "args": [ "-y", "@tidegap/mcp" ] } } } ``` ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-11-06 (score 88, +5) - [security improvement] Source repository: unverified → pass ### 2026-11-05 (score 83, −4) - [security regression] Provenance: pass → unverified ### 2026-11-03 (score 87, +5) - [security improvement] CVE-2023-54404 no longer affects this package - [security improvement] Known CVEs: fail → pass - [functional regression] Schema quality: 274 → 508 - [functional] Destructive annotations: pass → 100 - [functional] Package version: 0.19.0 → 0.20.0 ### 2026-11-02 (score 82, +1) No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-30 (score 81, +1) No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-28 (score 80, +1) No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-26 (score 79, +1) No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-24 (score 78, −5) - [security regression] CVE-2023-54404 affects this package: high - [security regression] Known CVEs: pass → fail ## MCP tools (12) ### `get_grid_forecast` (~286 tokens) Return the hour-by-hour grid carbon intensity forecast for one region, up to 72 hours ahead. Use when: the user asks how clean the grid is now or later, or wants the raw curve. Do not use to pick a run time for a task (use recommend_window) or to queue work (use schedule_task). Behavior: writes nothing; reads one grid feed, no login; GB is live without a key, other zones need a feed key or get synthetic data (Source: mock). Returns: region, source, generated time, one row per hour (gCO2/kWh and band), and the cleanest and dirtiest hour. Rejects an unknown zone and lists the closest zones. Input parameters: - `hours` (integer): How many hours ahead to forecast, e.g. 12 to cover "tonight". Defaults to 24; 72 is the most. - `region` (string, required): Grid zone code, e.g. 'US-CAL-CISO', 'GB' or 'DE'; take it from the user's location or the data center they name. `tidegap region list` prints the supported zones; any zone works with an Electricity M… ### `recommend_window` (~585 tokens) Preview the cleanest run window before a task's deadline, without queuing it. Use when: the user asks when a task would run or what waiting saves. Do not use to queue the task (use schedule_task) or for the raw hourly curve (use get_grid_forecast). Behavior: writes nothing; reads the grid forecast; no login or key. Returns: scheduled_for, intensity, band, estimated_carbon_g_co2, estimated_savings_vs_now_pct, batch_eligible, grid_source (mock = synthetic), alternatives, reasoning; routing_preview with 2+ candidates. Rejects a past deadline, an unknown zone, or a carbon_budget_g no window meets. Input parameters: - `candidates` (array): 'provider:model' pairs the user allows, e.g. ['anthropic:claude-haiku-4-5','ollama:llama-3-1-8b']. With 2 or more, the scheduler scores each at the chosen window on carbon, cost and latency (see rout… - `carbon_budget_g` (number): Hard cap on the task's estimated grams CO2e, e.g. 5. Windows above it are skipped; if no window before the deadline fits, the task fails instead of running on a dirty grid. Omit for no cap. - `deadline` (string, required): When the task must be finished: ISO-8601 with a UTC offset, in the future. Convert the user's words, e.g. "by 8am tomorrow" in New York becomes '2026-05-13T08:00:00-04:00'. - `model` (string): Model name to mention in the reasoning text, e.g. 'claude-sonnet-5'; it does not change the window. Omit to leave it out. - `region` (string, required): Grid zone the task would run against, e.g. 'US-CAL-CISO' or 'FR'. `tidegap region list` prints the supported zones; any zone works with an Electricity Maps key. Defaults, where the host lets it be om… - `route_weights` (object): How to rank candidates, e.g. {"carbon": 1} for carbon only. Weights are relative and normalized; a key left out counts as 0. Omit for the default {carbon: 0.6, cost: 0.3, latency: 0.1}. Ignored unles… ### `schedule_task` (~2831 tokens) Queue an AI task or recurring job to run at the cleanest grid hour before its deadline; long deadlines may use the provider Batch API. Use when: the user defers work ("tonight", "no rush", "before my limit resets") or wants it repeated ("every night", "daily", a cron); map that to deadline or repeat. Do not use for work the user waits on (do it now), to preview only (use recommend_window or dry_run) or for limits (use tidegap_usage). Behavior: adds one task, one run of one runner (dry_run writes nothing), or with repeat a job of such tasks; `tidegap tick` runs it; reads the grid forecast; no login; the result stays in the queue (check_queue_status). Returns: task_id, status, scheduled_for, deadline, provider, model, runs_in, estimated_carbon_g_co2, a readiness line; a job adds job_id and its guarantee. Rejects a past deadline, an unknown zone, disallowed tools and shell commands. Input parameters: - `after_limit_reset` (boolean): true when the user says "after my limit resets": the task starts no earlier than the Claude subscription limit reset (the latest reset of an exhausted 5-hour or weekly window, else the fuller window'… - `candidates` (array): 'provider:model' pairs the user allows, e.g. ['anthropic:claude-haiku-4-5','ollama:llama-3-1-8b']. With 2 or more, the scheduler scores each at the chosen window on carbon, cost and latency (see rout… - `carbon_budget_g` (number): Hard cap on the task's estimated grams CO2e, e.g. 5. Windows above it are skipped; if no window before the deadline fits, the task fails instead of running on a dirty grid. Omit for no cap. - `cwd` (string): Absolute folder a 'claude-code' run works in, e.g. a worktree '/work/app/.worktrees/fix-login'. This session's project folder keeps the run in a copy of this session; another folder runs fresh there,… - `days` (array): Weekdays for repeat 'weekly', e.g. ['mon','thu'] for "Mondays and Thursdays". Defaults to today's weekday in time_zone; omit for any other repeat. - `deadline` (string): When the task must be finished: ISO-8601 with a UTC offset, in the future. Convert the user's words, e.g. "by 8am tomorrow" in New York becomes '2026-05-13T08:00:00-04:00'. Omit with deadline_kind 'q… - `deadline_kind` (string): Defaults to 'absolute': the deadline parameter sets the due time. 'quota_reset' sets it to the next weekly subscription-quota reset minus a margin, from ~/.tidegap/config (TIDEGAP_QUOTA_RESET_