Skip to main content
Glama
Sign In

Fieldproxy

by io.github.Fieldproxy
OverviewDiscussionsAdmin

Server Details

Run field service from Claude, ChatGPT or Copilot: dispatch, billing, customer messages, photos, and change the software itself, with a confirm step before every change. This address is the India region; US East, Canada, Norway and NZ addresses are at fieldproxy.ai/mcp.

Ownership verified

The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status
Unhealthy
Uptime
77.9% over 42 days
Last Tested
Transport
Streamable HTTP
URL
Repository
Fieldproxy/fieldproxy-mcp
GitHub Stars
0
Server Listing
Fieldproxy MCP server
ChatGPT
–
Claude
–

TDQS

B3.1/5.0

Scored across 95 tools

Disambiguation3/5

Many tools are distinct, but several clusters overlap heavily: find_customers vs lookup_customers, churn_risk vs customer_churn_feedback_flags vs customer_churn_sentence_flags, ar_aging vs get_ar_aging, run_sql vs search_freeform vs export_csv, plan_day_routes vs plan_job_distribution vs dispatch_query, and multiple activity/usage admin tools. Descriptions give some differentiation, but an agent faces real misselection risk across these groups.

Naming Consistency3/5

Dominant verb_noun snake_case pattern (find_jobs, list_calls, get_call), but many non-verb or noun-only names (ar_aging, jobs_chart, rework_check, technician_jobs, ops_report) and inconsistent get_ vs find_ vs list_ for similar reads. Readable overall but noticeably mixed conventions.

Tool Count1/5

95 tools is an extreme mismatch for a single MCP server; many are near-duplicates or narrow admin analytics. This far exceeds any reasonable cognitive budget for an agent selecting among them.

Completeness4/5

The surface is remarkably broad, covering reads, SQL, routing, communications, documents, insights, admin audit, and scheduling plans with an explicit apply_schedule write path. It is if anything over-complete rather than lacking; only minor lifecycle gaps (e.g. direct update/delete outside propose_write) exist.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updates
    • Addedagent_task_detail
    • Addedagent_updates
    • Addedmy_agent_tasks
  2. 1 tool update
    • Addedcustomer_churn_sentence_flags
  3. 4 tool updates
    • Addedcalculate_route
    • Addedexplain_change
    • Addedgenerate_pdf
    • Addedlog_turn
  4. 5 tool updates
    • Addedextract_follow_ups_from_notes
    • Addedget_workspace_instructions
    • Addedjobs_chart
    • Addedops_report
    • Addedtriage_new_requests
  5. 82 tool updates
    • First observedactivity_summary
    • First observedai_activity_log
    • First observedai_usage_summary
    • First observedanalyze_funnel
    • First observedar_aging
    • First observedbroken_promises
    • First observedchurn_risk
    • First observedcompare_record
    • First observedcustomer_churn_feedback_flags
    • First observeddescribe_schema
    • First observeddispatch_query
    • First observeddrive_time
    • First observedexport_csv
    • First observedfind_communications
    • First observedfind_contracts
    • First observedfind_customers
    • First observedfind_invoices
    • First observedfind_jobs
    • First observedfind_quotes
    • First observedfind_technicians
    • First observedgenerate_document
    • First observedgenerate_estimate
    • First observedgeocode_address
    • First observedget_ar_aging
    • First observedget_automation_docs
    • First observedget_call
    • First observedget_insight_result
    • First observedget_tech_performance
    • First observedget_widget_docs
    • First observedintegration_status
    • First observedlist_activity_alert_rules
    • First observedlist_activity_alerts
    • First observedlist_ai_connections
    • First observedlist_ai_memory
    • First observedlist_alerts
    • First observedlist_calls
    • First observedlist_dashboards
    • First observedlist_deleted_records
    • First observedlist_distinct_values
    • First observedlist_document_templates
    • First observedlist_email_followups
    • First observedlist_email_templates
    • First observedlist_estimate_templates
    • First observedlist_insights
    • First observedlist_proposal_templates
    • First observedlist_proposals
    • First observedlist_record_files
    • First observedlist_saved_views
    • First observedlist_scheduled_reports
    • First observedlist_service_zones
    • First observedlookup_customers
    • First observednearest_technicians
    • First observedopen_record
    • First observedoverdue_tasks
    • First observedplan_day_routes
    • First observedplan_job_distribution
    • First observedpreview_proposal
    • First observedpriority_audit_from_text
    • First observedquotes_to_follow_up
    • First observedread_email_thread
    • First observedread_file
    • First observedrecord_history
    • First observedrevenue_by_month
    • First observedreverse_geocode
    • First observedrework_check
    • First observedrun_insight
    • First observedrun_sql
    • First observedsearch_freeform
    • First observedsearch_inbox
    • First observedsegment_customers
    • First observedtech_workload
    • First observedtechnician_jobs
    • First observedtechnician_locations
    • First observedtechnician_route
    • First observedtodays_schedule
    • First observedunbilled_completed_jobs
    • First observedunbilled_jobs_for_tech
    • First observedview_dashboard
    • First observedview_images
    • First observedworkspace_activity
    • First observedworkspace_usage
    • First observedzones_for_location

Related MCP Connectors

Related MCP Servers

  • PatrolTech MCP

    PatrolTech MCPofficial

    PatrolTech
    F
    license
    Not graded
    quality
    A
    maintenance
    Enables users to query live security patrol data and manage operations — rounds and missed rounds, QR/NFC checkpoint scans, routes and schedules, incidents, visitor logs and guard activity — from Claude, ChatGPT, Copilot, Gemini, Cursor or any MCP client. Write actions such as creating routes or checkpoints and updating incidents are staged as proposals that are only applied after the user confirms.
    -

  • Taskade MCP Server

    Leone542
    A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI assistants like Claude, Cursor, VS Code, and Windsurf to manage workspaces, projects, tasks, and AI agents through natural language, with a hosted OAuth server or a local stdio package. Also supports generating MCP tools from any OpenAPI spec.
    1,927 npm
    MIT

  • Narla MCP Connector

    madalinaagn-cell
    A
    license
    A
    quality
    C
    maintenance
    Lets teams operate their installed Narla AI agents from any MCP-capable assistant such as ChatGPT, Claude or Cursor, listing agents, tasks and business memory and drafting new tasks in plain language. Nothing executes until a human explicitly approves it, and every completed task retains a report of what the agent did and changed.
    6
    Apache 2.0

  • churchtools-mcp

    NoahDR
    A
    license
    B
    quality
    B
    maintenance
    Enables MCP clients such as Claude to read and manage persons, groups, calendars, events, and any of the 800+ ChurchTools API endpoints in a connected church instance using natural language. Reads execute immediately, while every write returns a preview of the intended change for approval before anything is committed, with one-time expiring tokens and a check for concurrent modifications.
    33
    7 npm
    1
    MIT
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.

Resources