FoundRole — AI Job Search & Application Tracker MCP for Claude & ChatGPT

Save a job to the tracker

tracker_add

Idempotent

Tracks a job from jobs_search results in the user's job tracker, identified by its job_id. For a job found elsewhere on the open web (with a URL but no jobs_search job_id), tracker_add_external is the right tool instead.

Fields:

job_id: the job ID from jobs_search results (required)
status: initial status (saved, applied, interviewing, offered, archived); defaults to "saved"
sub_status: sub-status within the main status: saved: interested, researching_company, preparing_application, ready_to_apply; applied: application_submitted, followed_up; interviewing: interview_scheduled, phone_screen, technical, onsite, final_round, pending_feedback; offered: negotiating, considering, offer_received, accepted; archived: ghosted, rejected_by_company, withdrawn_by_candidate, not_interested, employed_by_this_company, employed_by_another_company
notes: notes about the job

Returns the tracked job with its details. Repeated saves return the existing tracked job. A job that was previously removed from the tracker is restored with its earlier status and notes.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "job_id": "<job_id>"
    },
    "name": "tracker_add"
  }
}

Input Schema

Name	Required	Description
`notes`	No	Notes about this job
`job_id`	Yes	The job ID from jobs.search results
`status`	No	Initial tracking status: saved, applied, interviewing, offered, archived
`sub_status`	No	Sub-status within the main status, valid only for that status — saved: interested, researching_company, preparing_application, ready_to_apply; applied: application_submitted, followed_up; interviewing: interview_scheduled, phone_screen, technical, onsite, final_round, pending_feedback; offered: negotiating, considering, offer_received, accepted; archived: ghosted, rejected_by_company, withdrawn_by_candidate, not_interested, employed_by_this_company, employed_by_another_company
`result_item_id`	No	The result occurrence ID returned with the selected job

Output Schema

Name	Required	Description	Default
`hasMore`	No
`totalCount`	No
`trackedJob`	No
`statusOrder`	No
`trackedJobs`	No
`figureSources`	No
`trackerWebUrl`	No
`subStatusOrder`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedNov 10, 2026

addedOutput schema / properties / trackedJob / properties / appliedDateUnknown

Added value: +{
+  "description": "True for a job at the applied status with no stored applied date, unless the person said they do not remember it. FoundRole never fills that date in by itself; it comes from the person and tracker_update stores it in applied_at, or records in applied_date_declined that they do not remember it.",
+  "type": "boolean"
+}

addedOutput schema / properties / trackedJob / properties / daysSinceApplied

Added value: +{
+  "description": "Whole days since the applied date, counted in the user's time zone; null without an applied date.",
+  "type": [
+    "integer",
+    "null"
+  ]
+}

addedOutput schema / properties / trackedJob / properties / followUpDay

Added value: +{
+  "description": "Latest follow-up point, in days after applying, that a job still at the applied status has reached; null before the first point and for every other status. FoundRole never moves or archives a job by itself.",
+  "enum": [
+    7,
+    14,
+    21,
+    null
+  ],
+  "type": [
+    "integer",
+    "null"
+  ]
+}

addedOutput schema / properties / trackedJobs / items / properties / appliedDateUnknown

Added value: +{
+  "description": "True for a job at the applied status with no stored applied date, unless the person said they do not remember it. FoundRole never fills that date in by itself; it comes from the person and tracker_update stores it in applied_at, or records in applied_date_declined that they do not remember it.",
+  "type": "boolean"
+}

addedOutput schema / properties / trackedJobs / items / properties / daysSinceApplied

Added value: +{
+  "description": "Whole days since the applied date, counted in the user's time zone; null without an applied date.",
+  "type": [
+    "integer",
+    "null"
+  ]
+}

addedOutput schema / properties / trackedJobs / items / properties / followUpDay

Added value: +{
+  "description": "Latest follow-up point, in days after applying, that a job still at the applied status has reached; null before the first point and for every other status. FoundRole never moves or archives a job by itself.",
+  "enum": [
+    7,
+    14,
+    21,
+    null
+  ],
+  "type": [
+    "integer",
+    "null"
+  ]
+}

Changed1 schema field changedNov 3, 2026

addedOutput schema / properties / figureSources

Added value: +{
+  "properties": {
+    "estimatedSalary": {
+      "properties": {
+        "basis": {
+          "type": "string"
+        },
+        "methodologyUrl": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "ghostScore": {
+      "properties": {
+        "basis": {
+          "type": "string"
+        },
+        "methodologyUrl": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "methodologyUrl": {
+      "type": "string"
+    },
+    "source": {
+      "enum": [
+        "FoundRole"
+      ],
+      "type": "string"
+    },
+    "visaRecords": {
+      "properties": {
+        "basis": {
+          "type": "string"
+        },
+        "falseMeans": {
+          "type": "string"
+        },
+        "methodologyUrl": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "type": [
+    "object",
+    "null"
+  ]
+}

Changed1 schema field changedOct 8, 2026

addedInput schema / properties / result_item_id

Added value: +{
+  "description": "The result occurrence ID returned with the selected job",
+  "type": "string"
+}

AddedJul 27, 2026
RemovedJul 24, 2026

Changed1 schema field changedJul 22, 2026

changedInput schema / properties / sub_status / description

Previous value: -"Sub-status within the main status"New value: +"Sub-status within the main status, valid only for that status — saved: interested, researching_company, preparing_application, ready_to_apply; applied: application_submitted, followed_up; interviewing: interview_scheduled, phone_screen, technical, onsite, final_round, pending_feedback; offered: negotiating, considering, offer_received, accepted; archived: ghosted, rejected_by_company, withdrawn_by_candidate, not_interested, employed_by_this_company, employed_by_another_company"

Changed16 schema fields changedJul 21, 2026
- changedOutput schema / properties / trackedJob / properties / appliedAt / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / trackedJob / properties / createdAt / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / trackedJob / properties / deadline / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / trackedJob / properties / notes / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / trackedJob / properties / reminderAt / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / trackedJob / properties / salaryOfferedType / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / trackedJob / properties / subStatus / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / trackedJob / properties / updatedAt / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / trackedJobs / items / properties / appliedAt / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / trackedJobs / items / properties / createdAt / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / trackedJobs / items / properties / deadline / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / trackedJobs / items / properties / notes / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / trackedJobs / items / properties / reminderAt / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / trackedJobs / items / properties / salaryOfferedType / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / trackedJobs / items / properties / subStatus / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
- changedOutput schema / properties / trackedJobs / items / properties / updatedAt / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```

Changed3 schema fields changedJul 20, 2026

addedInput schema / $schema

Added value: +"https://json-schema.org/draft/2020-12/schema"

addedInput schema / additionalProperties
```
Added value: +false
```

addedOutput schema / $schema

Added value: +"https://json-schema.org/draft/2020-12/schema"

Changed6 schema fields changedJul 15, 2026

addedOutput schema / properties / hasMore
```
Added value: +{
+  "type": "boolean"
+}
```

addedOutput schema / properties / statusOrder

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedOutput schema / properties / subStatusOrder
```
Added value: +{
+  "type": "object"
+}
```
addedOutput schema / properties / totalCount
```
Added value: +{
+  "type": "integer"
+}
```

addedOutput schema / properties / trackedJobs

Added value: +{
+  "items": {
+    "properties": {
+      "appliedAt": {
+        "type": "string"
+      },
+      "contacts": {
+        "items": {
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "createdAt": {
+        "type": "string"
+      },
+      "deadline": {
+        "type": "string"
+      },
+      "id": {
+        "type": "string"
+      },
+      "isStarred": {
+        "type": "boolean"
+      },
+      "job": {
+        "type": [
+          "object",
+          "null"
+        ]
+      },
+      "notes": {
+        "type": "string"
+      },
+      "reminderAt": {
+        "type": "string"
+      },
+      "salaryOffered": {
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "salaryOfferedType": {
+        "type": "string"
+      },
+      "status": {
+        "type": "string"
+      },
+      "subStatus": {
+        "type": "string"
+      },
+      "tags": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "trackable": {
+        "type": [
+          "object",
+          "null"
+        ]
+      },
+      "updatedAt": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "id"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / trackerWebUrl
```
Added value: +{
+  "type": "string"
+}
```

Changed1 schema field changedJun 12, 2026

removedInput schema / properties / restore_removed

Removed value: -{
-  "description": "Set to true to restore a previously removed tracked job",
-  "type": "boolean"
-}

Changed1 schema field changedJun 10, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "trackedJob": {
+      "properties": {
+        "appliedAt": {
+          "type": "string"
+        },
+        "contacts": {
+          "items": {
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "createdAt": {
+          "type": "string"
+        },
+        "deadline": {
+          "type": "string"
+        },
+        "id": {
+          "type": "string"
+        },
+        "isStarred": {
+          "type": "boolean"
+        },
+        "notes": {
+          "type": "string"
+        },
+        "reminderAt": {
+          "type": "string"
+        },
+        "salaryOffered": {
+          "type": [
+            "number",
+            "null"
+          ]
+        },
+        "salaryOfferedType": {
+          "type": "string"
+        },
+        "status": {
+          "type": "string"
+        },
+        "subStatus": {
+          "type": "string"
+        },
+        "tags": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "trackable": {
+          "type": [
+            "object",
+            "null"
+          ]
+        },
+        "updatedAt": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "id"
+      ],
+      "type": "object"
+    }
+  },
+  "type": "object"
+}

First observedJun 3, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare write, non-destructive, idempotent and closed-world, so the baseline is lower; the description nonetheless adds real behavior: repeated saves return the existing tracked job, and a previously removed job is restored with its earlier status and notes. That restore-with-prior-state detail is genuinely non-obvious and not recoverable from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening routing sentence is well front-loaded, but the sub_status block is copied wholesale from the schema and consumes most of the description without adding interpretation. Roughly a third of the text could be deleted with no loss.

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

Completeness4/5

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

Covers the mutation, its idempotency, the restore case and what is returned, and an output schema exists so return shapes needn't be spelled out. Adequate for a 5-parameter create tool; only the untiered result_item_id parameter gets no narrative explanation.

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

Parameters3/5

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

Schema coverage is 100% and the description's field list largely restates it, including the long sub_status enumeration verbatim. The one piece of added meaning is that status defaults to "saved", which the schema does not state. Marginal value over the schema.

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?

States a specific verb and resource (tracks a job in the user's job tracker, identified by job_id) and immediately contrasts with the sibling tracker_add_external by input source (jobs_search job_id vs. open-web URL). An agent can route between the two without opening either schema.

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

Usage Guidelines4/5

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

Explicitly names the alternative and the condition that selects it (found elsewhere on the open web with a URL but no jobs_search job_id). Also clarifies the repeated-save and re-add cases. It does not touch routing against tracker_update or tracker_update_status, but the named alternative is the one that actually competes for the same input.

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

All FoundRole — AI Job Search & Application Tracker MCP for Claude & ChatGPT tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.