Skip to main content
Glama
Sign In
Iron Bridge Construction MCP Equipment Safety Server

Iron Bridge Construction MCP Equipment Safety Server

by mo7-s3d690
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Iron Bridge Construction — MCP Equipment Safety Server

Company & Problem

Iron Bridge Construction manages heavy equipment (cranes, excavators, scaffolding) across multiple job sites.
Before this system, site workers used paper checklists. Nothing stopped an uncertified operator from taking a crane, and nothing forced a human supervisor sign-off when the work was near power lines.

The fix: an MCP server that gives an LLM scoped, safe access to equipment data. The model never talks to the database directly. Every write that carries real risk is gated by capability checks, role changes, elicitation, and sampling.

Related MCP server: enterprise-agent-lab

Protocol Concerns Mapping

#

Concern

How it appears in this system

1

Capability negotiation

Server checks ctx.session.check_client_capability(...) for elicitation+sampling before attempting either, inside request_equipment's high-risk branch — not just via try/except after the fact. The demo client only gets this far because it registers real sampling_callback + elicitation_callback on ClientSession.

2

Notifications

Worker starts with read-only tools; approve_equipment_request is not registered at all. After authenticate_supervisor, the server calls mcp.add_tool(...) to register it for the first time, then pushes tools/list_changed. The tool set genuinely changes, not just the notification.

3

Elicitation

request_equipment for high-risk items (crane / near power lines) pauses mid-call and asks a human supervisor for explicit confirmation.

4

Resources

Safety policies (lifting-safety, electrical-proximity) are exposed as resources, not tools.

5

Prompts

Reusable template prepare-equipment-receipt that takes {request_id}.

6

Sampling

Before final approval of a high-risk request the server asks the client's model to draft a short risk summary; result is stored in audit log.

7

Progress tracking

generate_site_compliance_report walks every request and reports 25/50/75/100 %.

8

Defensive tool design

Strict JSON Schema (additionalProperties: false), server-side jsonschema validation, parameterized SQL, and handler-level authorization.

Transport

  • Development: stdio (default).

  • Demo / multi-site: Streamable HTTP (MCP_TRANSPORT=streamable-http).

Commit history shows the transition from stdio-only to HTTP support.

Quick Start

python -m venv .venv
source .venv/bin/activate   # or .venv\Scripts\Activate.ps1 on Windows
pip install -r requirements.txt
cp .env.example .env        # set SUPERVISOR_PIN; ANTHROPIC_API_KEY is optional
python db/init_db.py
python agent/client.py      # starts stdio server automatically

mcp is pinned to 1.29.0 in requirements.txt — mcp>=1.1.0 would let a fresh install pull mcp==2.0.0, which removed the fastmcp module this server is built on.

HTTP mode:

export MCP_TRANSPORT=streamable-http
export MCP_HOST=127.0.0.1
export MCP_PORT=8000
python -m mcp_server.server
# endpoint: http://127.0.0.1:8000/mcp

Tool Comparison

Tool

Read/Write

Needs elicitation?

Needs sampling?

Notes

check_worker_certification

read

no

no

always available

get_equipment_status

read

no

no

always available

request_equipment

write

yes if high-risk

yes if high-risk

creates PENDING request

authenticate_supervisor

write (session)

no

no

triggers tools/list_changed

approve_equipment_request

write

no

no

only after supervisor auth

generate_site_compliance_report

read (report)

no

no

progress updates

If a client connects without elicitation or sampling capability, high-risk requests return NOT_SUBMITTED and nothing is written to the database.

Folder Layout

db/                 schema, seed, ERD, init script
mcp_server/         server, schemas, service layer, database helpers
agent/              demo client that performs the full handshake
docs/               progressive code parts for team commits
issues/             ready-to-paste GitHub Issue bodies (one per concern)

Team Workflow (4 sequential parts per concern)

See docs/ and issues/. Each concern is an independent GitHub Issue.
Code for each concern is delivered in 4 progressive commits so every teammate has a visible contribution.

Tool Schema Changelog

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

Loading tool schema changelog…

    This server cannot be deployed

    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

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers

    • AgentGuard MCP Server

      vaasu202
      F
      license
      Not graded
      quality
      C
      maintenance
      Provides a secure MCP boundary for AI agents, intercepting and validating tool calls, redacting secrets, and requiring human approval for sensitive actions with a tamper-evident audit trail.
      -

    • enterprise-agent-lab

      isaac-dev-ai
      F
      license
      Not graded
      quality
      C
      maintenance
      Enables controlled AI-agent access to enterprise-shaped tools with a deny-by-default gated write path, human approval, dry-run execution, and append-only audit logging.
      1
      -

    • veor

      winterbim
      A
      license
      Not graded
      quality
      B
      maintenance
      Provides a governed execution boundary for AI agents, enforcing deterministic policy, one-shot human approvals, and signed receipts for MCP tool effects.
      MIT

    • io.github.amineutron/mcp-guard

      amineutron
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables LLM agents to safely invoke enterprise MCP tools under an enforceable guard that applies allowlist policies, caller roles, parameter restrictions, human confirmation for destructive operations, and a correlated JSONL audit log.
      AGPL 3.0