ITM Platform

io.github.itmplatformPublished by GitHub account itmplatformv1.0.22Updated Oct 27, 2026

Connect AI assistants to ITM Platform projects, tasks, budgets, risks, and team workload.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowData & Analytics

Overview

AI-generated overview

Connects AI assistants to ITM Platform to search projects, tasks, budgets, risks and workload, and to create or update project data.

What you can do
  • Search and read projects, services, tasks, users and reference data
  • Inspect budgets, purchases, revenues, risks, issues, progress and effort
  • Create and update projects, services, tasks, activities, risks and issues
  • Report task and project progress, log time entries and set planned effort
  • Bulk-update task or activity status and aggregate portfolio data
  • Run validated DataMart queries and use read-only resources and guided prompt templates
When to use it
Useful when your organization runs projects in ITM Platform and you want an assistant to answer portfolio questions, review budget and risk exposure, or carry out bulk project updates under your own permissions.
Requirements
Either the hosted remote endpoint with OAuth sign-in, or the local npm package run with npx, which needs Node.js 20 or later and the environment variables ITM_API_URL, ITM_COMPANY and ITM_API_KEY (an API key generated in ITM Platform). A licensed ITM Platform account is required; Team Member licenses are blocked.
Before you install
Write tools create and change projects, tasks, risks, issues and time entries, and bulk updates can change up to 100 items per call; a 100% project progress entry auto-closes the project. API key sessions carry the full permissions of the user who generated the key. Project data is sent to the AI client you choose, so that provider's data-handling policy applies.

Installation

In SourceWeft

  1. Open ITM Platform in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.itmplatform%2Fmcp-server/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "itm-platform": {
      "type": "http",
      "url": "https://api.itmplatform.com/v2/_/mcp/"
    }
  }
}

README

ITM Platform MCP Server

Connect ITM Platform to AI assistants through the Model Context Protocol. The ITM Platform MCP server lets MCP-compatible clients search projects, inspect budgets, summarize portfolio health, create tasks, log risks and issues, and update project details using your ITM Platform permissions.

It works with Claude, VS Code, Cursor, OpenAI Codex, Windsurf, JetBrains AI Assistant, and any other client that supports MCP.

Quick Start

Hosted connection with OAuth

Use the hosted server if your AI client supports remote MCP servers. There is nothing to install: add the URL, sign in with your ITM Platform account, and approve the requested access.

bash
claude mcp add --scope user --transport http itm-platform https://api.itmplatform.com/v2/_/mcp/

For other MCP clients, use this remote URL:

text
https://api.itmplatform.com/v2/_/mcp/

OAuth is the recommended setup for most users because your AI client never sees your ITM Platform password or API key.

After adding the server, open your AI client, type /mcp where slash commands are supported, select itm-platform, and complete the ITM Platform OAuth login when prompted.

Local connection with an API key

Use the npm package if you prefer to run the server locally, work behind a firewall, or need to connect to a self-hosted ITM Platform instance.

bash
npx @itm-platform/mcp-server

Your MCP client must pass these environment variables to the server:

VariableValue
ITM_API_URLhttps://api.itmplatform.com
ITM_COMPANYYour company/account slug
ITM_API_KEYYour personal API key from ITM Platform

Example stdio configuration:

json
{  "mcpServers": {    "itm-platform": {      "command": "npx",      "args": ["@itm-platform/mcp-server"],      "env": {        "ITM_API_URL": "https://api.itmplatform.com",        "ITM_COMPANY": "{your-account}",        "ITM_API_KEY": "your-api-key"      }    }  }}

To create an API key, log in to ITM Platform, open My Profile, and generate a key from the API Key section.

After configuring the local server, restart your AI client and use /mcp or the client's MCP server list to confirm itm-platform is connected.

What Can an Agent Do?

From simple lookups to fully automated cross-system workflows, MCP unlocks progressively more powerful use cases.

Quick lookup -- Ask a question, get an answer:

"What risks are open across my portfolio?"

Multi-step analysis -- The agent chains multiple tools and synthesizes results:

"Review every project ending this quarter. Flag any with budget overruns, open high-impact risks, or task completion below 60%."

Automated bulk actions -- The agent reads, decides, and writes across projects:

"For every project still in Planning status with a start date in the past, update the status to Execution and create a kick-off checklist task assigned to the project manager."

Scheduled intelligence -- An agent runs on a schedule with no human prompt, pulling overdue tasks every Monday and posting a summary to Slack grouped by project manager.

Cross-system orchestration -- Combine ITM Platform's MCP with other MCP servers (GitHub, Slack, Google Calendar, email). When a developer merges a PR, an agent finds the matching ITM Platform task, marks it complete, and if the project hits 100%, drafts a closure summary and emails the program manager.

The MCP server authenticates as you, calls ITM Platform APIs, and returns only the data your ITM Platform account is allowed to access.

Capabilities

The server exposes 47 MCP tools, 6 resources, and 4 prompt templates.

Read Tools

ToolWhat it does
search_projectsFind projects by name, status, type, or date range
get_projectRetrieve project details with subcomponent counts and optional budget
search_servicesFind services by name, status, type, or date range
get_serviceRetrieve service details with subcomponent counts and optional budget
list_project_tasksList tasks for a project with pagination
get_taskRetrieve full detail of a single task
search_tasksSearch tasks across all projects by name, status, assignee, kind, or date range
get_project_budgetGet budget, actuals, revenue, cost, and margin information
get_project_purchasesList purchase orders for a project with pagination
get_project_revenuesList revenue items for a project with pagination
get_project_risksList project risks with pagination
get_project_issuesList project issues with pagination
get_riskRetrieve full detail of a single risk, including mitigation and contingency plans
get_issueRetrieve full detail of a single issue, including resolution and impact fields
list_task_progressList the progress (follow-up) history for a task
get_task_effortGet a task's effort breakdown per team member and per professional category; doubles as the task team list
get_project_progressGet project progress report: expected, baseline, and actual curves; optionally the full project Seguimiento entries
list_service_activitiesList activities for a service with pagination
get_service_purchasesList purchase orders for a service with pagination
get_service_revenuesList revenue items for a service with pagination
aggregate_portfolioGroup and summarize portfolio data
query_datamartRun validated DataMart queries for advanced analysis
search_usersFind users and team members; returns IsNonLoginUser so non-login users (empty EmailAddress) can be addressed by UserId
get_userRetrieve user details
get_reference_dataRetrieve statuses, types, priorities, and other reference lists
get_custom_fieldsRetrieve the account's custom field definitions for projects, tasks, risks, issues, services, activities, purchases, or revenues
get_custom_field_optionsRetrieve the selectable options of a dropdown custom field

Write Tools

ToolWhat it does
create_projectCreate a project (Waterfall or Kanban); the project starts with the account default status and the creating user as project manager
create_taskAdd a task, milestone (KindId 1), or summary task (KindId 2); ParentId builds Gantt hierarchy on Waterfall projects; TaskManagers/TaskMembers assign users by username or numeric UserId (the id is the only option for non-login users)
update_taskUpdate task fields such as status, dates, kind, and parent; TaskManagers/TaskMembers add assignees by username or numeric UserId (add-only, never removes)
create_task_progressReport progress on a task (percentage, assessment, notes) with full side effects
update_task_progressUpdate an existing task progress entry
update_task_effortSet the estimated (planned) hours of a task per assigned user; accepted effort and billing data are preserved
log_time_entryLog actual worked hours on a task for one user and date; adds to or replaces the day's total, echoing previous and new totals
create_project_progressCreate a project-level progress (Seguimiento) entry: percentage, assessment, and status description; 100% auto-closes the project
update_project_progressUpdate an existing project progress entry
create_riskLog a project risk
update_riskUpdate risk fields such as status, probability, impact, level, and mitigation or contingency plans
create_issueLog a project issue with a required issue type and status
update_issueUpdate issue fields such as status, type, and resolution
update_projectUpdate project fields such as name, status, dates, and priority
create_serviceCreate a service; it starts with the account default status
update_serviceUpdate service fields such as name, status, dates, and priority
create_activityAdd an activity to a service (activities form a flat list)
update_activityUpdate activity fields such as status and dates
bulk_update_task_statusApply one status to up to 100 tasks of a project in a single call
bulk_update_activity_statusApply one status to up to 100 activities of a service in a single call

Write operations confirm the saved state from the ITM Platform REST API. DataMart-backed search results may take up to 60 seconds to reflect recent writes. Validation failures include the actionable message returned by REST instead of only the HTTP status.

Data source routing

Reads come from DataMart whenever DataMart holds the data (quota-free, portfolio-wide); REST is reserved for data DataMart lacks, single-item authoritative reads (get_task), write readbacks, and reference data. Writes always go to REST. When DataMart gains a dataset, the matching GET tools must migrate to DataMart. Full rule and current routing map: zz_Specifications/progress-history-reads-from-datamart.md.

When the account defines custom fields, each session is enriched with per-account context: the server lists the DataMart customFields keys actually in use in the MCP initialize instructions and in the query_datamart tool description, so agents can read and filter custom field values without prior discovery.

Resources and Prompts

Resources give AI clients read-only context such as DataMart schemas and project calendars. Prompt templates provide guided workflows for common analysis tasks:

PromptWhat it helps with
/project_statusSummarize health, tasks, risks, issues, and budget for one project
/portfolio_overviewAnalyze portfolio status, methodology, budget, and delivery patterns
/team_workloadReview assignments and workload patterns
/risk_analysisAssess risk exposure, issues, and budget impact

Authentication and Permissions

The MCP server uses the same identity and permission model as ITM Platform.

Connection methodAuthenticationBest for
Hosted HTTPOAuth 2.1 with PKCEMost users and managed AI clients
Local stdioITM Platform API keyLocal execution, firewalled networks, self-hosted environments

OAuth sessions use scopes:

ScopeAllows
mcp:readRead-only tools such as search, get, list, aggregate, and query
mcp:writeRead tools plus create and update tools

API key sessions use the full permissions of the ITM Platform user who generated the key.

License access:

LicenseMCP access
Company AdminFull read and write access
Full UserFull read and write access
Project ManagerRead and write access scoped to managed projects
Team MemberBlocked

Your AI assistant does not receive your ITM Platform password or API key. Project data is returned to the AI client you choose, so the AI provider's data-handling policy applies to any data it processes.

Client Setup

Use the public docs for client-specific setup:

For any MCP-compatible client, the two connection values are:

MethodValue
Remote URLhttps://api.itmplatform.com/v2/_/mcp/
Local commandnpx @itm-platform/mcp-server

After adding either connection, open the client's MCP command or server list. In clients that support slash commands, type /mcp, select itm-platform, and authenticate when prompted.

Self-Hosting

For a local stdio server, configure ITM_API_URL, ITM_COMPANY, and either ITM_API_KEY or ITM_TOKEN.

For an HTTP server with OAuth, configure:

VariableDescription
ITM_API_URLITM Platform API gateway URL
PORTHTTP listen port
ITM_AUTH_URLOAuth authorization server URL used for token exchange
ITM_AUTH_PUBLIC_URLPublic OAuth URL advertised to AI clients
MCP_SERVER_URLPublic MCP server URL used as the OAuth audience
LOG_LEVELOptional Pino log level: debug, info, warn, or error
ITM_AUDIT_ENABLEDEnables server-side audit logging when set to true
ITM_UI_URLOptional ITM Platform UI base URL (e.g. https://app.itmplatform.com); when set, create_project returns a uiUrl deep link to the created project

When deployed behind a reverse proxy, ITM_AUTH_URL can point to a server-to-server address while ITM_AUTH_PUBLIC_URL must be reachable by AI clients.

Development

Requirements:

  • Node.js 20 or later
  • npm

Install dependencies, run tests, and build:

bash
npm installnpm testnpm run build

Run the HTTP development server:

bash
cp .env.sample .envnpm run dev

The package entry point is dist/server.js; the npm executable is mcp-server.

Troubleshooting

If tools do not appear in your AI client, confirm that the server configuration is in the correct file for that client, restart the client, and check that npx @itm-platform/mcp-server runs successfully for local setups.

If authentication fails, regenerate your API key or reconnect the OAuth server so your client receives a fresh token.

OAuth sessions automatically retry once on a downstream 401 by re-exchanging the OAuth bearer token for a fresh session token. This handles cases where the session token is invalidated externally (e.g. by a concurrent browser login). If 401 errors persist, the OAuth bearer token itself has likely expired and the AI client needs to re-authenticate.

If a write succeeds but a later search shows old data, wait up to 60 seconds. Writes are confirmed from the REST API immediately, while DataMart search indexes update asynchronously.

More Help

Source: README.md at commit ee0316a

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

2
  1. v1.0.22LatestSep 29, 2026
  2. v1.0.3Sep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts