Skip to content

projectstate MCP server

Which MCP servers are projectstate's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-26

← Back to projectstate

Whose server it is
  • Registry nameonline.projectstate/projectstateverified in the MCP registry

The registry name sits under projectstate.online. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-26
  • Stateanswerschecked 2026-10-26
  • Tools6
  • Server calls itselfprojectstate
  • Server version0.3.0
  • Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 120 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: keep decisions, failed attempts and open tasks across agent sessions; check a planned step against past failures and decisions; recall relevant project notes with keyword search under a budget.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • For "keep decisions, failed attempts and open tasks across agent sessions", the likely first call is project_open.
  • For "check a planned step against past failures and decisions", the likely first call is plan_check.
  • For "recall relevant project notes with keyword search under a budget", the likely first call is recall.
  • update change data without a sign-in: anyone with the address can call them.
  • Parameters are untyped or undescribed in 6 of 6 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 2, the first on 2026-10-26
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer281 ms
  • Space in an agent's context≈ 1,472 tokensthe definitions of all its tools (6), which an agent carries on every turn
  • Tool definitionsC · 67 of 100
  • Typed results6 of 6 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 6 of 6
  • Not saying whether it only reads or can destroy: 6 of 6

What an agent can do with it

  • can do · keep decisions, failed attempts and open tasks across agent sessions
  • can do · check a planned step against past failures and decisions
  • can do · recall relevant project notes with keyword search under a budget

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

  • Tools that change data, on a server that answers without a sign-in: update

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers6 tools · read 2026-10-26
  • project_open

    Open (or create) a project and get a compact brief: status line, open tasks, latest active decisions and failed attempts. Call this first in a session. Omit `project` to list your projects. `project` is a slug like 'my-app' (lowercase…

  • project_status

    Get the project's one-line status, open tasks and last change. Pass `set_status` to overwrite the status line (e.g. 'v0.3 shipped; next: migrate auth to OAuth'). Cheap; use it for handoff notes between sessions.

  • remember

    Store one fact about the project. `kind` is one of: decision (what was chosen and why), attempt (something tried; status 'worked'|'failed'|'partial'), task (status 'open'|'done'|'dropped'), note (anything else). `title` is one line; put…

  • recall

    Search the project's memory with keywords and get the few most relevant entries (ranked, active entries first, superseded ones last), trimmed to `max_chars`. Use 2-5 specific keywords (e.g. 'auth token expiry'). Filters: kind…

  • plan_check

    Before you start something non-trivial, say what you are about to do and get back only what would change your mind: attempts that already failed at this, decisions that are still in force and constrain it, and open tasks that overlap…

  • update

    Change an existing entry by id: set `status` (task open|done|dropped, attempt worked|failed|partial, decision active|superseded|reverted, note active|archived), replace `title`/`body`, `append` a line to the body (e.g. an outcome)…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "projectstate": {
      "type": "http",
      "url": "https://projectstate.online/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http projectstate https://projectstate.online/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://projectstate.online/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.