PerfLens MCP Server

Overview Schema Source Related Servers Discussions Admin

collect_profile

Destructive

Run bounded Linux performance collection (record, stat, sched, lock, off-CPU) after explicit authorization to gather evidence for performance analysis.

Instructions

Run bounded perf record/stat/sched/lock/off-CPU collection only after explicit server and per-call authorization.

Input Schema

TableJSON Schema

Name	Required	Default
`pid`	No
`mode`	No	record
`events`	No
`call_graph`	No	dwarf
`executable`	No
`output_path`	Yes
`frequency_hz`	No
`authorization`	Yes
`timeout_seconds`	No
`duration_seconds`	No
`max_output_bytes`	No
`target_arguments`	No
`pid_authorization`	No

Output Schema

TableJSON Schema

Name	Required	Default
`uri`	Yes
`summary`	Yes
`artifact_id`	Yes
`artifact_type`	Yes
`schema_version`	No	1.0
`evidence_quality`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedv0.3.2Aug 28, 2026

addedOutput schema / $defs / EvidenceQuality / properties / kernel_context_self_percent

Added value: +{
+  "anyOf": [
+    {
+      "maximum": 100,
+      "minimum": 0,
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Kernel Context Self Percent"
+}

addedOutput schema / $defs / EvidenceQuality / properties / kernel_context_self_weight

Added value: +{
+  "anyOf": [
+    {
+      "minimum": 0,
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Kernel Context Self Weight"
+}

addedOutput schema / $defs / EvidenceQuality / properties / unknown_context_self_percent

Added value: +{
+  "anyOf": [
+    {
+      "maximum": 100,
+      "minimum": 0,
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Unknown Context Self Percent"
+}

addedOutput schema / $defs / EvidenceQuality / properties / unknown_context_self_weight

Added value: +{
+  "anyOf": [
+    {
+      "minimum": 0,
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Unknown Context Self Weight"
+}

addedOutput schema / $defs / EvidenceQuality / properties / unresolved_kernel_self_percent

Added value: +{
+  "anyOf": [
+    {
+      "maximum": 100,
+      "minimum": 0,
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Unresolved Kernel Self Percent"
+}

addedOutput schema / $defs / EvidenceQuality / properties / unresolved_kernel_self_weight

Added value: +{
+  "anyOf": [
+    {
+      "minimum": 0,
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Unresolved Kernel Self Weight"
+}

addedOutput schema / $defs / EvidenceQuality / properties / unresolved_unknown_context_self_percent

Added value: +{
+  "anyOf": [
+    {
+      "maximum": 100,
+      "minimum": 0,
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Unresolved Unknown Context Self Percent"
+}

addedOutput schema / $defs / EvidenceQuality / properties / unresolved_unknown_context_self_weight

Added value: +{
+  "anyOf": [
+    {
+      "minimum": 0,
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Unresolved Unknown Context Self Weight"
+}

addedOutput schema / $defs / EvidenceQuality / properties / unresolved_user_self_percent

Added value: +{
+  "anyOf": [
+    {
+      "maximum": 100,
+      "minimum": 0,
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Unresolved User Self Percent"
+}

addedOutput schema / $defs / EvidenceQuality / properties / unresolved_user_self_weight

Added value: +{
+  "anyOf": [
+    {
+      "minimum": 0,
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Unresolved User Self Weight"
+}

addedOutput schema / $defs / EvidenceQuality / properties / user_context_self_percent

Added value: +{
+  "anyOf": [
+    {
+      "maximum": 100,
+      "minimum": 0,
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "User Context Self Percent"
+}

addedOutput schema / $defs / EvidenceQuality / properties / user_context_self_weight

Added value: +{
+  "anyOf": [
+    {
+      "minimum": 0,
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "User Context Self Weight"
+}

Changed3 schema fields changedv0.3.0Aug 21, 2026

changedInput schema / properties / events / default

Previous value: -[
-  "cycles",
-  "instructions",
-  "cache-references",
-  "cache-misses",
-  "branches",
-  "branch-misses",
-  "context-switches",
-  "cpu-migrations",
-  "page-faults"
-]New value: +[
+  "cycles",
+  "instructions",
+  "cache-references",
+  "cache-misses",
+  "branches",
+  "branch-misses",
+  "task-clock",
+  "context-switches",
+  "cpu-migrations",
+  "page-faults"
+]

addedOutput schema / $defs

Added value: +{
+  "EvidenceQuality": {
+    "additionalProperties": false,
+    "properties": {
+      "actual_event_source": {
+        "default": "unknown",
+        "enum": [
+          "hardware",
+          "software",
+          "unknown"
+        ],
+        "title": "Actual Event Source",
+        "type": "string"
+      },
+      "address_annotation_line_count": {
+        "minimum": 0,
+        "title": "Address Annotation Line Count",
+        "type": "integer"
+      },
+      "aggregated_frame_occurrence_count": {
+        "minimum": 0,
+        "title": "Aggregated Frame Occurrence Count",
+        "type": "integer"
+      },
+      "allowed_conclusions": {
+        "default": [],
+        "items": {
+          "type": "string"
+        },
+        "title": "Allowed Conclusions",
+        "type": "array"
+      },
+      "call_graph_weight": {
+        "minimum": 0,
+        "title": "Call Graph Weight",
+        "type": "integer"
+      },
+      "call_graph_weight_percent": {
+        "maximum": 100,
+        "minimum": 0,
+        "title": "Call Graph Weight Percent",
+        "type": "number"
+      },
+      "collection_limitations": {
+        "default": [],
+        "items": {
+          "type": "string"
+        },
+        "title": "Collection Limitations",
+        "type": "array"
+      },
+      "duplicate_frame_line_count": {
+        "minimum": 0,
+        "title": "Duplicate Frame Line Count",
+        "type": "integer"
+      },
+      "event": {
+        "title": "Event",
+        "type": "string"
+      },
+      "exported_call_path_count": {
+        "minimum": 0,
+        "title": "Exported Call Path Count",
+        "type": "integer"
+      },
+      "exported_hotspot_count": {
+        "minimum": 0,
+        "title": "Exported Hotspot Count",
+        "type": "integer"
+      },
+      "fallback_reason": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Fallback Reason"
+      },
+      "fallback_used": {
+        "anyOf": [
+          {
+            "type": "boolean"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Fallback Used"
+      },
+      "forbidden_conclusions": {
+        "default": [],
+        "items": {
+          "type": "string"
+        },
+        "title": "Forbidden Conclusions",
+        "type": "array"
+      },
+      "frame_line_count": {
+        "minimum": 0,
+        "title": "Frame Line Count",
+        "type": "integer"
+      },
+      "inline_frame_count": {
+        "minimum": 0,
+        "title": "Inline Frame Count",
+        "type": "integer"
+      },
+      "input_bytes": {
+        "minimum": 0,
+        "title": "Input Bytes",
+        "type": "integer"
+      },
+      "input_sha256": {
+        "pattern": "^[a-f0-9]{64}$",
+        "title": "Input Sha256",
+        "type": "string"
+      },
+      "limitations": {
+        "default": [],
+        "items": {
+          "type": "string"
+        },
+        "title": "Limitations",
+        "type": "array"
+      },
+      "malformed_record_count": {
+        "minimum": 0,
+        "title": "Malformed Record Count",
+        "type": "integer"
+      },
+      "normalization_merge_count": {
+        "minimum": 0,
+        "title": "Normalization Merge Count",
+        "type": "integer"
+      },
+      "omitted_call_path_weight": {
+        "minimum": 0,
+        "title": "Omitted Call Path Weight",
+        "type": "integer"
+      },
+      "omitted_hotspot_self_weight": {
+        "minimum": 0,
+        "title": "Omitted Hotspot Self Weight",
+        "type": "integer"
+      },
+      "parser_invariants_passed": {
+        "title": "Parser Invariants Passed",
+        "type": "boolean"
+      },
+      "quality_status": {
+        "enum": [
+          "verified",
+          "partial"
+        ],
+        "title": "Quality Status",
+        "type": "string"
+      },
+      "sample_count": {
+        "minimum": 0,
+        "title": "Sample Count",
+        "type": "integer"
+      },
+      "schema_version": {
+        "const": "1.0",
+        "default": "1.0",
+        "title": "Schema Version",
+        "type": "string"
+      },
+      "source_annotation_line_count": {
+        "minimum": 0,
+        "title": "Source Annotation Line Count",
+        "type": "integer"
+      },
+      "source_collection_artifact_sha256": {
+        "anyOf": [
+          {
+            "pattern": "^[a-f0-9]{64}$",
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Source Collection Artifact Sha256"
+      },
+      "source_collection_id": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Source Collection Id"
+      },
+      "source_line_frame_count": {
+        "minimum": 0,
+        "title": "Source Line Frame Count",
+        "type": "integer"
+      },
+      "source_line_self_percent": {
+        "maximum": 100,
+        "minimum": 0,
+        "title": "Source Line Self Percent",
+        "type": "number"
+      },
+      "source_line_self_weight": {
+        "minimum": 0,
+        "title": "Source Line Self Weight",
+        "type": "integer"
+      },
+      "source_locations_truncated_hotspot_count": {
+        "minimum": 0,
+        "title": "Source Locations Truncated Hotspot Count",
+        "type": "integer"
+      },
+      "total_call_path_count": {
+        "minimum": 0,
+        "title": "Total Call Path Count",
+        "type": "integer"
+      },
+      "total_hotspot_count": {
+        "minimum": 0,
+        "title": "Total Hotspot Count",
+        "type": "integer"
+      },
+      "total_weight": {
+        "minimum": 0,
+        "title": "Total Weight",
+        "type": "integer"
+      },
+      "unicode_replacement_count": {
+        "minimum": 0,
+        "title": "Unicode Replacement Count",
+        "type": "integer"
+      },
+      "unresolved_self_percent": {
+        "maximum": 100,
+        "minimum": 0,
+        "title": "Unresolved Self Percent",
+        "type": "number"
+      },
+      "unresolved_self_weight": {
+        "minimum": 0,
+        "title": "Unresolved Self Weight",
+        "type": "integer"
+      },
+      "warning_count": {
+        "minimum": 0,
+        "title": "Warning Count",
+        "type": "integer"
+      },
+      "warnings_truncated": {
+        "title": "Warnings Truncated",
+        "type": "boolean"
+      },
+      "weight_source": {
+        "title": "Weight Source",
+        "type": "string"
+      },
+      "weight_unit": {
+        "title": "Weight Unit",
+        "type": "string"
+      }
+    },
+    "required": [
+      "quality_status",
+      "parser_invariants_passed",
+      "input_sha256",
+      "input_bytes",
+      "sample_count",
+      "total_weight",
+      "event",
+      "weight_unit",
+      "weight_source",
+      "malformed_record_count",
+      "warning_count",
+      "warnings_truncated",
+      "unicode_replacement_count",
+      "frame_line_count",
+      "duplicate_frame_line_count",
+      "address_annotation_line_count",
+      "source_annotation_line_count",
+      "aggregated_frame_occurrence_count",
+      "unresolved_self_weight",
+      "unresolved_self_percent",
+      "call_graph_weight",
+      "call_graph_weight_percent",
+      "source_line_frame_count",
+      "source_line_self_weight",
+      "source_line_self_percent",
+      "inline_frame_count",
+      "normalization_merge_count",
+      "source_locations_truncated_hotspot_count",
+      "total_hotspot_count",
+      "exported_hotspot_count",
+      "omitted_hotspot_self_weight",
+      "total_call_path_count",
+      "exported_call_path_count",
+      "omitted_call_path_weight"
+    ],
+    "title": "EvidenceQuality",
+    "type": "object"
+  }
+}

addedOutput schema / properties / evidence_quality

Added value: +{
+  "anyOf": [
+    {
+      "$ref": "#/$defs/EvidenceQuality"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

Changed1 schema field changedv0.2.0Aug 7, 2026
- changedInput schema / properties / max_output_bytes / default
```
Previous value: -1073741824New value: +268435456
```
First observedv0.1.0Aug 1, 2026

TDQS

B3.3/5.0

Behavior3/5

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

Given the destructiveHint=true annotation, the description adds useful context by emphasizing bounded collection and the need for explicit server and per-call authorization. However, it does not disclose what the destructive behavior actually consists of, such as what happens to output_path or what side effects attaching perf to a process may have.

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

Conciseness5/5

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

A single sentence with no filler, front-loading the action and scoping it to bounded perf collection before stating the authorization gate. Every phrase earns its place.

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

Completeness2/5

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

The output schema lightens return-value expectations, but this is a destructive 13-parameter tool with 35 siblings and zero schema descriptions. The definition omits prerequisite/alternative guidance and key parameter-selection semantics, so an agent cannot confidently invoke it correctly from this description alone.

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

Parameters2/5

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

Schema description coverage is 0%, so the description carries the full burden for parameter meaning, but it only hints at the mode values ('record/stat/sched/lock/off-CPU') and the authorization requirement. It leaves pid vs. executable vs. target_arguments selection, call_graph tradeoffs, duration/timeout semantics, and output_path expectations unexplained.

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?

The description is specific: it names the verb ('Run'), the resource class (bounded perf record/stat/sched/lock/off-CPU collection), and the authorization prerequisite. This clearly differentiates it from the docker- and project-level collect_* siblings, which collect different kinds of data.

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

Usage Guidelines2/5

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

The only guidance is the precondition that explicit server and per-call authorization must exist before invoking the tool. There is no when-to-use-this-vs-alternatives guidance, no mention of the many sibling collect/analyze tools, and no exclusions or fallback paths.

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

Deploy Server