Skip to main content
Glama
TylerIlunga

Procore MCP Server

List Near Misses

list_near_misses
Read-onlyIdempotent

List near miss records for a project, optionally scoped to an incident, to review hazard details and get record IDs for further actions.

Instructions

Returns a paginated list of near miss records for the specified project, optionally scoped to a single incident via incident_id. Each near miss includes description, affected person, harm source, potential for injury details, and custom fields. By default sorted by descending full_number (incident.number). Supports filtering by affected party, harm source, managed equipment, and full-text search. Use this to discover near misses or to look up the id of one before calling a tool that needs it. project_id defaults to the value set by procore_set_config when omitted. Returns a JSON array of near misses; page and per_page control pagination and the response reports how many pages remain. Read-only — it changes nothing in Procore. Failures come back as an error payload carrying the HTTP status — commonly 401 when the token has expired, 403 without tool permission, and 404 when an id does not resolve. Required parameters: project_id. Procore API: Project Management > Incidents. Endpoint: GET /rest/v1.0/projects/{project_id}/incidents/near_misses

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoQuery string parameter — page number for paginated results (default: 1)
sortNoQuery string parameter — sort order for results. Prefix with '-' for descending order
per_pageNoQuery string parameter — number of items per page (default: 100, max: 100)
project_idYesURL path parameter — unique identifier for the project.
incident_idNoQuery string parameter — optional incident ID to scope results. When provided, returns only near miss records belonging to the specified incident. Omit to retrieve near misses across all incidents in the project.
filters__queryNoQuery string parameter — full-text search across near miss description and related fields. Returns near misses where any searchable field contains the query string.
filters__created_atNoQuery string parameter — return item(s) created within the specified ISO 8601 datetime range. Formats: `YYYY-MM-DD`...`YYYY-MM-DD` - Date `YYYY-MM-DDTHH:MM:SSZ`...`YYYY-MM-DDTHH:MM:SSZ` - DateTime with UTC Offset `YYYY-MM-...
filters__harm_source_idNoQuery string parameter — array of Harm Source IDs. Returns item(s) with the specified Harm Source IDs.
filters__work_activity_idNoQuery string parameter — array of Work Activity IDs. Returns item(s) with the specified Work Activity IDs.
filters__affected_party_idNoQuery string parameter — array of Affected Party IDs. Returns item(s) with the specified Affected Party IDs.
filters__affected_person_idNoQuery string parameter — array of Person IDs. Returns item(s) with the specified affected Person IDs.
filters__affected_company_idNoQuery string parameter — array of Company IDs. Returns item(s) with the specified affected Company IDs.
filters__managed_equipment_idNoQuery string parameter — return item(s) with the specified Managed Equipment ID.
Behavior5/5

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

Beyond the annotations (readOnlyHint, idempotentHint, openWorldHint, destructiveHint), the description discloses pagination behavior (page/per_page, pages remaining), default sorting, project_id defaulting, and detailed error scenarios with HTTP status codes. It explicitly states 'Read-only — it changes nothing in Procore,' reinforcing the safety profile without contradicting annotations.

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?

Although substantial, every sentence contributes value: function, inclusion list, default sort, filters, use case, project_id default, response format, read-only guarantee, error handling, required parameter, and API endpoint. The description is front-loaded and logically organized, making it easy for an agent to parse key facts quickly.

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?

Given no output schema, the description compensates well by describing the return type (JSON array), included fields, pagination reporting, and common error responses. It covers the essential behavioral context for a listing tool, making it sufficient for an agent to select and invoke correctly.

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 baseline is 3. The description adds meaningful semantics beyond the schema: project_id defaults to procore_set_config when omitted, incident_id scoping behavior, and the meaning of page/per_page in controlling pagination. It does not elaborate on every filter's format, but the schema already covers that.

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 uses a specific verb ('Returns a paginated list') and a clear resource ('near miss records for the specified project'), with optional scoping via incident_id. It clearly distinguishes this tool from sibling tools like create_near_miss, show_near_miss, and update_near_miss by its read-only listing behavior.

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?

Provides explicit guidance: 'Use this to discover near misses or to look up the id of one before calling a tool that needs it.' This tells the agent exactly when to invoke it and implies the alternative of calling a follow-up tool. It also mentions project_id defaulting from procore_set_config, which is an important contextual prerequisite.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/TylerIlunga/procore-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server