forecast-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | Interface to bind (HTTP mode only). | 0.0.0.0 |
| PORT | No | Port to listen on (HTTP mode only). Setting this alone is enough to switch to HTTP mode. | 3000 |
| MCP_TRANSPORT | No | Set to 'http' to force HTTP mode even without PORT. | |
| MCP_ALLOWED_HOSTS | No | Comma-separated list of allowed Host header values, for DNS-rebinding protection when binding to a non-localhost address. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| forecast_durationA | Run a Monte Carlo simulation over a list of tasks, each with an optimistic / most-likely / pessimistic duration, to produce a probabilistic forecast of the TOTAL project duration. Returns P50/P80/P90/P95, mean, standard deviation, and a distribution shape. Optionally give a |
| forecast_costA | Run a Monte Carlo simulation over a list of cost line items, each with an optimistic / most-likely / pessimistic amount, to produce a probabilistic forecast of the TOTAL budget. Returns P50/P80/P90/P95, mean, standard deviation, and a distribution shape. Optionally give a |
| forecast_completionA | Answer 'when will it be done?' from historical throughput instead of per-task estimates. Give the number of items completed in each recent period (e.g. stories per sprint) and the remaining backlog; the tool bootstraps future periods to forecast how many periods are needed to clear the backlog. Returns P50/P80/P90/P95 in periods, and calendar dates when a start date and period length are supplied. Optionally model scope creep with |
| pert_estimateA | Compute a classic PERT estimate from tasks with optimistic / most-likely / pessimistic values. Returns each task's expected value and standard deviation, the rolled-up project mean and standard deviation, and the value achievable at each confidence level (via a normal approximation). Instant and deterministic - use it for a quick estimate or to cross-check a Monte Carlo forecast. Assumes tasks are independent and summed. |
| sensitivity_analysisA | Identify which tasks contribute most to the uncertainty in a project total. Runs the Monte Carlo simulation and, for each task, computes its correlation with the total and its share of the total variance. Returns tasks ranked from biggest to smallest driver, so you know where reducing estimate uncertainty or de-risking the work has the most impact. This is the data behind a tornado chart. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a distinct purpose: duration, cost, throughput-based completion, deterministic PERT, and sensitivity/variance contribution. Although forecast_duration and pert_estimate both estimate duration, the descriptions clearly distinguish Monte Carlo vs deterministic normal approximation, and forecast_duration vs forecast_cost differ by resource type.
All names use consistent snake_case, which is readable and predictable. However, three tools follow a forecast_ object pattern while pert_estimate and sensitivity_analysis use different noun-based patterns, so it is not a uniform verb_noun convention throughout.
Five tools is well-scoped for a project-forecasting server. Each tool covers a genuinely different estimation method or output, with no redundant or filler tools.
The surface covers duration, cost, completion timeline from throughput, quick deterministic estimation, and uncertainty drivers. Together these address the core lifecycle of probabilistic project forecasting with no obvious missing operation.