Server definition

Hash: sha256:1ab5542b4653bd542e87d9109ba9d9dcad4fe8d156f11f34e029186b07ce734a
What it is: What a remote MCP server returned when asked what it offers: 4 tools

The blob, as servednamed by its sha256

{
  "instructions": "AI Layoffs publishes an open, source-cited register of layoffs linked to AI (2023 to date) and a live 0-100 index of AI job-loss pressure. All tools are read-only and free to use.\n\nWhich tool answers which question: the current reading or trend -> get_ai_layoffs_index; 'how many jobs has AI replaced' -> count_ai_job_losses; one company -> get_company_ai_layoffs; lists, filters and recent events -> search_ai_layoff_events.\n\nHow to read the fields:\n\nattribution (who tied the cut to AI). explicit: The company itself declared the layoff AI-related. blamed: A credible source named AI, but the company did not. Shown as context and never counted: prong 1 of our standard requires the employer's own source to name AI, so a blamed event is a failed claim, not a discounted one. mixed: AI was cited alongside other material factors (cost, demand).\nevidence_tier (how strong the source is). tier1 (Primary-source attributed): AI named as a workforce driver in the company's own SEC filing, on-record earnings call, or official statement, with the event corroborated by a structured source. tier2 (Reputable-press attributed): AI named as a cause by credible journalism quoting a named company source, but not yet in a company filing. tier3 (Inferred / single-source): Attribution from one secondary tracker, an unnamed source, or vague forward-looking language.\nexecution (did it happen). executed: The reduction has been carried out. partial: Some of the cut is done, the rest pending. announced: A stated plan, not yet carried out (often multi-year). unknown: Execution status not established. reversed: The cut was rolled back or rehired against (e.g. Commonwealth Bank).\nroles_counted vs roles_reported_not_counted: counted roles meet the register's AI-attribution standard and enter the totals; reported roles are the figure reported for the cut (stated by the employer, or by the press where the reason says so) that the register does not count, because the cause or the figure fails its standard, and each such event's not_counted_reason says which. Where the roles are never decides counting: a counted figure with no US breakdown counts worldwide and stays out of the US index sum.\n\nReading results correctly: every figure carries its scope (worldwide or US) and its period; an announced plan is not a completed cut (see execution); each event links its source (source.url) and its page on the site (page_url); get_ai_layoffs_index returns the citation string for the index. A company absent from the register has no recorded AI-linked event, which is not evidence that it made no layoffs.",
  "tools": [
    {
      "description": "Answers 'how many jobs has AI replaced (or cost) this year?' with the register's published count: roles disclosed in layoffs linked to AI, roles where the employer itself named AI, the evidence-weighted headline figure, and the independent Challenger, Gray & Christmas count of US cuts attributed to AI. Each figure carries its scope (worldwide or US), its period and its definition, plus the ready-made answer sentence. The totals are computed over the whole register, so they are the published figures, not a sum of search results. Takes no arguments.",
      "inputSchema": {
        "properties": {},
        "type": "object"
      },
      "name": "count_ai_job_losses",
      "outputSchema": null
    },
    {
      "description": "Current reading of the AI Layoffs Index, a 0-100 score of AI-attributed job-loss pressure scaled against AI's own history since 2023 (not a share of all jobs). Returns the value, its band, the uncertainty range, the change vs last month, the three weighted components with what each reads, the as-of date, and a ready-made citation string. Takes no arguments.",
      "inputSchema": {
        "properties": {},
        "type": "object"
      },
      "name": "get_ai_layoffs_index",
      "outputSchema": null
    },
    {
      "description": "Did a specific company cut jobs because of AI? Returns the register's verdict for that company (explicit, mixed or blamed), the roles it disclosed vs the roles counted as AI-attributed, and every recorded event with the employer's own words and source. Accepts a company name such as 'Klarna' or 'Salesforce'. If the company is not in the register, says so and what that does and does not mean.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "company": {
            "description": "Company name, e.g. 'Klarna', 'IBM', 'Salesforce'. Partial names work.",
            "maxLength": 120,
            "minLength": 1,
            "pattern": "\\S",
            "type": "string"
          }
        },
        "required": [
          "company"
        ],
        "type": "object"
      },
      "name": "get_company_ai_layoffs",
      "outputSchema": null
    },
    {
      "description": "Search the source-cited register of layoffs linked to AI (one row per event, 2023 to date). Filter by company, free text, attribution, evidence tier, execution status, country, sector, affected role and date range; call with no arguments for the most recent events. Each event returns the employer's own stated reason (claim), roles counted vs reported but not counted, execution status, and a link to its source and its ailayoffs.org company page; set full_context for each event's longer context paragraph.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "attribution": {
            "description": "Keep only these attribution levels. explicit: The company itself declared the layoff AI-related. blamed: A credible source named AI, but the company did not. Shown as context and never counted: prong 1 of our standard requires the employer's own source to name AI, so a blamed event is a failed claim, not a discounted one. mixed: AI was cited alongside other material factors (cost, demand).",
            "items": {
              "enum": [
                "explicit",
                "mixed",
                "blamed"
              ],
              "type": "string"
            },
            "type": "array"
          },
          "company": {
            "description": "Company name or part of it, e.g. 'Klarna'.",
            "maxLength": 120,
            "pattern": "\\S",
            "type": "string"
          },
          "counted_only": {
            "description": "Only events whose roles the register counts as AI-attributed (drops events that are reported but not counted).",
            "type": "boolean"
          },
          "country": {
            "description": "Country as recorded, partial match, e.g. 'United States', 'India', 'Sweden'. For US-based roles use us_only.",
            "maxLength": 80,
            "pattern": "\\S",
            "type": "string"
          },
          "evidence_tier": {
            "description": "Keep only these evidence tiers. tier1 (Primary-source attributed): AI named as a workforce driver in the company's own SEC filing, on-record earnings call, or official statement, with the event corroborated by a structured source. tier2 (Reputable-press attributed): AI named as a cause by credible journalism quoting a named company source, but not yet in a company filing. tier3 (Inferred / single-source): Attribution from one secondary tracker, an unnamed source, or vague forward-looking language.",
            "items": {
              "enum": [
                "tier1",
                "tier2",
                "tier3"
              ],
              "type": "string"
            },
            "type": "array"
          },
          "execution": {
            "description": "Keep only these execution statuses. executed: The reduction has been carried out. partial: Some of the cut is done, the rest pending. announced: A stated plan, not yet carried out (often multi-year). unknown: Execution status not established. reversed: The cut was rolled back or rehired against (e.g. Commonwealth Bank).",
            "items": {
              "enum": [
                "executed",
                "partial",
                "announced",
                "reversed",
                "unknown"
              ],
              "type": "string"
            },
            "type": "array"
          },
          "full_context": {
            "description": "Also return each event's context paragraph. Several times longer, so best with a small limit; get_company_ai_layoffs always includes it for one company.",
            "type": "boolean"
          },
          "limit": {
            "description": "Maximum events to return (default 10, at most 50).",
            "maximum": 50,
            "minimum": 1,
            "type": "integer"
          },
          "query": {
            "description": "Free text matched against the company, the stated reason, the context paragraph, sector, country, affected roles and source name. Every word must appear. Example: 'customer service'.",
            "maxLength": 200,
            "pattern": "\\S",
            "type": "string"
          },
          "role": {
            "description": "Affected function or occupation, partial match, e.g. 'customer service', 'engineering'.",
            "maxLength": 80,
            "pattern": "\\S",
            "type": "string"
          },
          "sector": {
            "description": "Sector, partial match, e.g. 'Financial', 'Software'.",
            "maxLength": 80,
            "pattern": "\\S",
            "type": "string"
          },
          "since": {
            "description": "Earliest event date, inclusive: YYYY, YYYY-MM or YYYY-MM-DD.",
            "pattern": "^\\d{4}(-\\d{2}(-\\d{2})?)?$",
            "type": "string"
          },
          "sort": {
            "description": "newest first (default), oldest first, or the largest disclosed cut first.",
            "enum": [
              "newest",
              "oldest",
              "largest"
            ],
            "type": "string"
          },
          "until": {
            "description": "Latest event date, inclusive: YYYY, YYYY-MM or YYYY-MM-DD.",
            "pattern": "^\\d{4}(-\\d{2}(-\\d{2})?)?$",
            "type": "string"
          },
          "us_only": {
            "description": "Only events whose affected roles are US-based.",
            "type": "boolean"
          }
        },
        "type": "object"
      },
      "name": "search_ai_layoff_events",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:1ab5542b4653bd542e87d9109ba9d9dcad4fe8d156f11f34e029186b07ce734a | sha256sum