A
licenseA
qualityC
maintenanceEnables AI assistants to forecast revenue and demand for Shopify stores using Google's TimesFM model. Provides tools for revenue forecasting, demand analysis, promotion analysis, and anomaly detection.
7
1
MIT
forecast-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@forecast-mcpForecast next 3 months from this monthly revenue data"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
timesfm-mcp
MCP server for Google's TimesFM 2.5 — give any AI agent zero-config time-series forecasting.
Plug TimesFM 2.5, Google's 200M-parameter foundation model for time-series, directly into Claude Code, Claude Desktop, Cursor, or any MCP client. The agent calls forecast, gets point predictions + uncertainty bands + a trend/seasonality summary, and writes the explanation itself.
No ML configuration. No data pipelines. One line to run.
Chart generated with the statistical baseline. See "Enable TimesFM 2.5" below to use the full neural model.
Quickstart (30 seconds)
uvx timesfm-mcp # runs over stdio for local agentsAdd to your Claude Desktop / Claude Code / Cursor config:
{
"mcpServers": {
"forecast": { "command": "uvx", "args": ["timesfm-mcp"] }
}
}Then ask your agent: "Forecast the next 6 months from this revenue data and tell me what to expect."
Related MCP server: Nixtla MCP Server
Enable TimesFM 2.5 (optional)
System requirements: ≥ 16 GB RAM · ~800 MB disk (model weights, downloaded on first use) · PyTorch
Not sure? Skip this —
uvx timesfm-mcpalready works great on any machine.
pip install "timesfm-mcp[timesfm]"The TimesFM 2.5 source is bundled inside this package (Apache-2.0, Google LLC) — no separate git clone needed. The server auto-detects it and upgrades automatically; no config change required.
Two backends, zero config
Backend | When active | System requirement | Install |
Statistical baseline | Always — default | Any machine |
|
TimesFM 2.5 (Google) | When installed | ≥ 16 GB RAM + ~800 MB disk |
|
Start with the baseline. It runs on any machine, installs in seconds, and delivers production-ready forecasts. Upgrade to TimesFM only if you need the neural model's extra accuracy and have the RAM for it.
Tools
Tool | What it does |
| Forecast a single series with optional uncertainty bands |
| Report which engine is active (timesfm / baseline) |
| Hold out the last N points — compare TimesFM vs baseline MAE/sMAPE |
Supported clients
Works with any MCP-compatible agent. Verified configs in Client Setup:
Client | Config |
Claude Desktop |
|
Claude Code |
|
GitHub Copilot (VS Code) |
|
Cursor |
|
Windsurf |
|
Cline (VS Code) | Cline MCP settings panel |
Continue.dev |
|
Zed |
|
Documentation
Full docs in the docs/ folder:
Getting Started — installation and first forecast
Client Setup — config for all 8 supported clients
Tool Reference — full parameter docs
Cookbook — SaaS MRR, e-commerce demand, traffic, cloud spend
How It Works — the math and model
Migrating from forecast-mcp
timesfm-mcp is the renamed continuation of forecast-mcp. Update your install:
pip install timesfm-mcp # replaces: pip install forecast-mcp
uvx timesfm-mcp # replaces: uvx forecast-mcpUpdate your agent config: change "args": ["forecast-mcp"] → "args": ["timesfm-mcp"].
License
Apache-2.0
Available Tools
3 toolsbacktestB
Hold out the last N points and compare TimesFM vs baseline performance.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| values | Yes | Historical observations (at least holdout + 3 points). | |
| holdout | No | Number of final points to hold out for testing. |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
TDQS
B3.4/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description must disclose behavioral traits. It mentions comparing performance but does not specify metrics, side effects, data sufficiency requirements, or output format. The existence of an output schema may fill some gaps, but the description itself is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that concisely conveys the core action. It is front-loaded and efficient, though a bit more detail could be added without harming brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and the presence of an output schema, the description is adequate but lacks details such as what baseline is used or what performance metrics are computed. This might leave some ambiguity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema coverage, the schema already documents both parameters adequately. The description adds context about the comparison (TimesFM vs baseline) but does not enhance parameter meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs a backtest by holding out the last N points and comparing TimesFM performance against a baseline. This distinguishes it from sibling tools 'forecast' (making predictions) and 'list_backends' (enumerating backends).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for model evaluation via holdout validation, but it does not explicitly state when to use it instead of alternatives like 'forecast' or list conditions where it is not appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
forecastC
Forecast a single numeric time series.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| values | Yes | The historical observations in chronological order (oldest first). | |
| horizon | No | How many future steps to predict. | |
| quantiles | No | Symmetric coverage levels for uncertainty bands, e.g. [0.9]. Omit for point forecasts only. | |
| season_length | No | Known seasonal period (e.g. 7 for daily-with-weekly, 12 for monthly-with-yearly). Leave null to auto-detect. |
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
TDQS
C2.6/5.0
Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only states 'Forecast a single numeric time series', omitting details on side effects, permissions, error conditions, or return behavior. The agent is left with no insight into the operation's implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (6 words), but conciseness comes at the cost of missing critical details. It lacks structure (e.g., sections) and could benefit from a slightly longer explanation of expected inputs and outputs.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that an output schema exists, the description could offload some detail, but it still fails to mention that it returns forecasts, how many, or any assumptions. The tool is simple, but more context is needed for reliable use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond what the schema already provides for each parameter. It simply repeats the concept of a time series forecast.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (forecast) and resource (single numeric time series). It is concise and unambiguous, but lacks differentiation from sibling tools like 'backtest' and 'list_backends', though the purpose is still apparent.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, context, or exclusions, leaving the agent without direction for appropriate invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_backendsA
Report which forecasting engine is active and why.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
ParametersJSON Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
TDQS
A3.9/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It only reveals that the tool reports engine status ('which' and 'why'), but does not disclose potential side effects, permissions needed, cost, or response details beyond purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, concise sentence that is front-loaded and contains no extraneous words. Every part earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple (no params, has output schema), and the description adequately states its purpose. However, it could be more precise about what 'why' entails (e.g., context or reason for engine choice). The presence of an output schema reduces the need to describe return values.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With zero parameters and schema coverage 100%, the baseline is 4. The description adds meaning by clarifying that the tool requires no input and reports both the active engine and the reason, effectively compensating for the lack of parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb 'report' and clearly identifies the resource ('forecasting engine'). It explains what the tool does (active engine and why), which distinguishes it from siblings 'backtest' and 'forecast' that perform different actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use versus when not to use. The usage context is implied by the sibling tool names (backtest, forecast), but the description does not state conditions or alternatives, resulting in only implied usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
B3.4/5.0
Disambiguation5/5
Each tool has a distinct, non-overlapping purpose: backtesting, forecasting, and engine info. No ambiguity between them.
Naming Consistency4/5
All tools use imperative verbs, but 'backtest' and 'forecast' are single words while 'list_backends' uses an underscore. Slight inconsistency in formatting.
Tool Count5/5
Three tools is well-scoped for a focused forecasting server. Each tool is essential and contributes to the core workflow.
Completeness4/5
Covers the main actions: forecast, backtest, and engine info. Minor gaps like listing available models or settings, but acceptable for this domain.
Maintenance
ActivityInactive
ResponsivenessNo issues
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
60+ units, live FX, timezones, and date arithmetic for AI agents.
SEO & marketing toolkit for AI agents: GA4, Search Console, AdSense, GTM, PageSpeed, Trends.
PredictOracle - 12 forecasting tools: time-series, scenario analysis, risk projections.
Macroeconomic and FX time-series data for AI agents: indicators, calendars, COT, forex, commodities.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables multitenant time series forecasting and anomaly detection using Nixtla's TimeGPT, with support for fine-tuning, rolling backtests, and usage tracking.MIT
- AlicenseAqualityBmaintenanceDeterministic time-series statistics for AI agents. This MCP server gives any LLM agent unit-tested statistical tools — anomaly detection, changepoint detection, seasonal decomposition, stationarity/trend tests, data-quality audits, baseline forecasts — with schema-validated structured output and no arbitrary code execution.17MIT
- AlicenseNot gradedqualityCmaintenanceEnables time-series analysis and forecasting through a structured tool catalogue, including data loading, quality repair, diagnostics, and forecasting with ARIMA, exponential smoothing, Chronos-2, Toto 2.0, and AutoML.1MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ramdhavepreetam/timesfm-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server