Skip to main content
Glama

Create a watched project

create_project

Create a project: a site MeshArc re-crawls on a schedule, comparing each run with the last to record pages added, modified and removed. Use it when asked to monitor or track a site; for a one-off read use crawl_site. Check list_projects first so the site is not added twice. Inputs: seed starts a new project, e.g. 'example.com'. crawl_id instead keeps a crawl_site crawl from the last day as the first run, with no second fetch; it keeps that crawl's settings, so config goes only with seed -- except its page limit: the crawl's limit was how much to look at once, so the project gets a project's default (100, within the plan), which update_project changes. The usual config keys are include_paths (one section, e.g. ['/blog/*']), exclude_paths, max_pages and render_js; get_project with no project_id lists them all. Cost: creating reads robots.txt and the sitemaps but no pages, so it is free. Each run spends credits per page, and any schedule but 'manual' runs on its own. Caps: max_credits_per_run stops a run at that many credits, keeping what it read; max_credits_per_month skips scheduled runs once the month has spent that many. 0 or omitted is no cap. Refusals: an unknown config key, or a plan already at its project limit (code plan_limit). Values above the plan's caps are lowered to them. Needs write access; a read-only connection is refused with code 'read_only'.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoA display name; omit for the site's host (or the crawl's own name).
seedNoThe site to watch, as a URL or bare domain, e.g. 'https://example.com/blog/' or 'example.com'; its host is fixed for good. Give this or crawl_id.
configNoSettings as {key: value}, with a seed only; omit for the defaults.
crawl_idNoA crawl_site answer's crawl_id, to keep that crawl as the project. Give this or seed.
scheduleNoHow often it re-crawls on its own; 'manual' (default) runs only when start_run is called.manual
max_credits_per_runNoThe most one run may spend, in credits; omit or 0 for no cap.
max_credits_per_monthNoThe most its runs may spend in a calendar month, in credits; omit or 0 for no cap.

Output Schema

NameRequiredDescriptionDefault
idNoThe project's 32-character hex id.
codeNoOnly on a failure: a machine-readable reason, e.g. read_only, validation, plan_limit or not_found.
hostNoThe site it covers; fixed at creation.
nameNoIts display name.
noteNoNo project_id only: how path globs work.
seedNoWhere its crawls start.
errorNoOnly when the call failed: what went wrong, in words an assistant can act on.
pagesNoPages its last finished run read, a number.
configNoIts settings as {key: value}; secrets such as chat_url come back masked. create_project and update_project list only the settings that differ from the defaults; get_project lists them all.
detailNoOnly on a failure: the API's own wording, when the error was rephrased.
statusNodraft, crawling, healthy or failing. On an error, the HTTP status code.
purgeAtNoWhen an archived project is deleted for good (ISO 8601), or null.
archivedNotrue for an archived project: it runs no more and is deleted on purgeAt unless restored.
coverageNoPercent of the site the last run reached; under 90 means removals are withheld.
settingsNoNo project_id only: every common setting as {key, meaning, default}.
webhooksNoget_project only: {url, events, deliveries}: where run and change events are POSTed, which events, and the last 10 deliveries, each {id, event, status (queued, retrying, delivered or failed), attempts, lastStatus, lastError, createdAt, deliveredAt}. The signing secret is never included.
lastRunAtNoWhen the last run started (ISO 8601), or null.
nextRunAtNoWhen the schedule runs it next, or null for manual.
retentionNoHow long runs are kept, e.g. '90d'.
schedulesNoNo project_id only: the valid schedules.
archivedAtNoWhen it was archived (ISO 8601), or null.
configNoteNocreate_project and update_project only: says that config lists only the non-default settings.
other_keysNoNo project_id only: further keys accepted but rarely needed.
scheduleKeyNomanual, hourly, daily or weekly.
webhookTestNoupdate_project with test_webhook only: {queued, id} when a test run.finished message was queued, or {error, status} when the API refused it, e.g. with no webhook URL saved.
changeSummaryNoThe last compared run in words, e.g. '3 new · 2 changed · 0 removed'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedOutput schema / properties / archived
      Added value: +{
      +  "description": "true for an archived project: it runs no more and is deleted on purgeAt unless restored.",
      +  "title": "Archived"
      +}
    • addedOutput schema / properties / archivedAt
      Added value: +{
      +  "description": "When it was archived (ISO 8601), or null.",
      +  "title": "Archivedat"
      +}
    • changedOutput schema / properties / config / description
      Previous value: -"Its settings as {key: value}; secrets such as chat_url come back masked."New value: +"Its settings as {key: value}; secrets such as chat_url come back masked. create_project and update_project list only the settings that differ from the defaults; get_project lists them all."
    • addedOutput schema / properties / configNote
      Added value: +{
      +  "description": "create_project and update_project only: says that config lists only the non-default settings.",
      +  "title": "Confignote"
      +}
    • addedOutput schema / properties / purgeAt
      Added value: +{
      +  "description": "When an archived project is deleted for good (ISO 8601), or null.",
      +  "title": "Purgeat"
      +}
  2. Changed4 schema fields changed
    • addedInput schema / properties / max_credits_per_month
      Added value: +{
      +  "anyOf": [
      +    {
      +      "minimum": 0,
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "The most its runs may spend in a calendar month, in credits; omit or 0 for no cap.",
      +  "title": "Max Credits Per Month"
      +}
    • addedInput schema / properties / max_credits_per_run
      Added value: +{
      +  "anyOf": [
      +    {
      +      "minimum": 0,
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "The most one run may spend, in credits; omit or 0 for no cap.",
      +  "title": "Max Credits Per Run"
      +}
    • addedOutput schema / properties / pages
      Added value: +{
      +  "description": "Pages its last finished run read, a number.",
      +  "title": "Pages"
      +}
    • removedOutput schema / properties / pagesN
      Removed value: -{
      -  "description": "Pages its last finished run read.",
      -  "title": "Pagesn"
      -}
  3. Changed3 schema fields changed
    • changedOutput schema / description
      Previous value: -"A project, or with no project_id the settings any project can take."New value: +"A project, as get_project, create_project and update_project answer with it; get_project with no\nproject_id answers with the settings any project can take instead."
    • addedOutput schema / properties / webhookTest
      Added value: +{
      +  "description": "update_project with test_webhook only: {queued, id} when a test run.finished message was queued, or {error, status} when the API refused it, e.g. with no webhook URL saved.",
      +  "title": "Webhooktest"
      +}
    • addedOutput schema / properties / webhooks
      Added value: +{
      +  "description": "get_project only: {url, events, deliveries}: where run and change events are POSTed, which events, and the last 10 deliveries, each {id, event, status (queued, retrying, delivered or failed), attempts, lastStatus, lastError, createdAt, deliveredAt}. The signing secret is never included.",
      +  "title": "Webhooks"
      +}
  4. Changed9 schema fields changed
    • changedInput schema / properties / config / description
      Previous value: -"Any subset of the settings describe_project_config lists. For one section of a site pass include_paths, e.g. {\"include_paths\": [\"/blog/*\"]}; map_site shows the site's sections first. Omit for the defaults."New value: +"Settings as {key: value}, with a seed only; omit for the defaults."
    • addedInput schema / properties / crawl_id
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "A crawl_site answer's crawl_id, to keep that crawl as the project. Give this or seed.",
      +  "title": "Crawl Id"
      +}
    • changedInput schema / properties / name / description
      Previous value: -"A name for the project; omit to use the site's host name."New value: +"A display name; omit for the site's host (or the crawl's own name)."
    • addedInput schema / properties / seed / anyOf
      Added value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedInput schema / properties / seed / default
      Added value: +null
    • changedInput schema / properties / seed / description
      Previous value: -"Where the crawl starts: a public site's URL or bare domain, e.g. 'https://example.com/blog/' or 'example.com'. The project covers that host."New value: +"The site to watch, as a URL or bare domain, e.g. 'https://example.com/blog/' or 'example.com'; its host is fixed for good. Give this or crawl_id."
    • removedInput schema / properties / seed / type
      Removed value: -"string"
    • removedInput schema / required
      Removed value: -[
      -  "seed"
      -]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "description": "A project, or with no project_id the settings any project can take.",
      +  "properties": {
      +    "changeSummary": {
      +      "description": "The last compared run in words, e.g. '3 new · 2 changed · 0 removed'.",
      +      "title": "Changesummary"
      +    },
      +    "code": {
      +      "description": "Only on a failure: a machine-readable reason, e.g. read_only, validation, plan_limit or not_found.",
      +      "title": "Code"
      +    },
      +    "config": {
      +      "description": "Its settings as {key: value}; secrets such as chat_url come back masked.",
      +      "title": "Config"
      +    },
      +    "coverage": {
      +      "description": "Percent of the site the last run reached; under 90 means removals are withheld.",
      +      "title": "Coverage"
      +    },
      +    "detail": {
      +      "description": "Only on a failure: the API's own wording, when the error was rephrased.",
      +      "title": "Detail"
      +    },
      +    "error": {
      +      "description": "Only when the call failed: what went wrong, in words an assistant can act on.",
      +      "title": "Error"
      +    },
      +    "host": {
      +      "description": "The site it covers; fixed at creation.",
      +      "title": "Host"
      +    },
      +    "id": {
      +      "description": "The project's 32-character hex id.",
      +      "title": "Id"
      +    },
      +    "lastRunAt": {
      +      "description": "When the last run started (ISO 8601), or null.",
      +      "title": "Lastrunat"
      +    },
      +    "name": {
      +      "description": "Its display name.",
      +      "title": "Name"
      +    },
      +    "nextRunAt": {
      +      "description": "When the schedule runs it next, or null for manual.",
      +      "title": "Nextrunat"
      +    },
      +    "note": {
      +      "description": "No project_id only: how path globs work.",
      +      "title": "Note"
      +    },
      +    "other_keys": {
      +      "description": "No project_id only: further keys accepted but rarely needed.",
      +      "title": "Other Keys"
      +    },
      +    "pagesN": {
      +      "description": "Pages its last finished run read.",
      +      "title": "Pagesn"
      +    },
      +    "retention": {
      +      "description": "How long runs are kept, e.g. '90d'.",
      +      "title": "Retention"
      +    },
      +    "scheduleKey": {
      +      "description": "manual, hourly, daily or weekly.",
      +      "title": "Schedulekey"
      +    },
      +    "schedules": {
      +      "description": "No project_id only: the valid schedules.",
      +      "title": "Schedules"
      +    },
      +    "seed": {
      +      "description": "Where its crawls start.",
      +      "title": "Seed"
      +    },
      +    "settings": {
      +      "description": "No project_id only: every common setting as {key, meaning, default}.",
      +      "title": "Settings"
      +    },
      +    "status": {
      +      "description": "draft, crawling, healthy or failing. On an error, the HTTP status code.",
      +      "title": "Status"
      +    }
      +  },
      +  "title": "ProjectOut",
      +  "type": "object"
      +}
  5. Changed5 schema fields changed
    • addedInput schema / properties / config / description
      Added value: +"Any subset of the settings describe_project_config lists. For one section of a site pass include_paths, e.g. {\"include_paths\": [\"/blog/*\"]}; map_site shows the site's sections first. Omit for the defaults."
    • addedInput schema / properties / name / description
      Added value: +"A name for the project; omit to use the site's host name."
    • addedInput schema / properties / schedule / description
      Added value: +"How often it re-crawls on its own; 'manual' (default) runs only when start_run is called."
    • addedInput schema / properties / schedule / enum
      Added value: +[
      +  "manual",
      +  "hourly",
      +  "daily",
      +  "weekly"
      +]
    • addedInput schema / properties / seed / description
      Added value: +"Where the crawl starts: a public site's URL or bare domain, e.g. 'https://example.com/blog/' or 'example.com'. The project covers that host."
  6. First observed

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare it is a non-read-only, non-idempotent, open-world write. The description goes well beyond that: creation reads robots.txt and sitemaps but no pages so it is free, each run spends credits per page, non-manual schedules fire automatically, caps truncate a run while keeping what it read, over-plan values are silently lowered, and write access is required with specific refusal codes ('read_only', 'plan_limit'). That is exactly the operational context annotations cannot carry.

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?

Front-loaded with the purpose, then labelled blocks (Inputs, Cost, Caps, Refusals) that make scanning easy, and no filler sentences. The Inputs section is a single dense sentence with an embedded '-- except' aside about the page limit that takes a second pass to parse, which is the only structural cost.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with seven optional parameters, the definition covers cost, scheduling behaviour, cap semantics, silent value clamping, auth requirements, error codes, and the seed-vs-crawl_id decision. Return values need not be explained since an output schema exists, so nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, and the description earns above that by documenting cross-parameter semantics the schema cannot express: config applies only with seed, not crawl_id, and the inherited crawl's page limit is deliberately replaced by the project default of 100, changeable via update_project. The config key list (include_paths, exclude_paths, max_pages, render_js) is also supplied because the schema types config as an open object.

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?

Opens with a concrete verb and resource and defines the concept the tool creates: a site re-crawled on a schedule, diffing each run to record pages added, modified and removed. It explicitly contrasts itself with crawl_site for one-off reads, so an agent can distinguish it from siblings without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives the trigger ('when asked to monitor or track a site'), the alternative and its condition ('for a one-off read use crawl_site'), and a prerequisite ('check list_projects first so the site is not added twice'). It also states the either/or between seed and crawl_id, so the agent knows both when to use the tool and which input path to take.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.