How do I use Rathbones Reconciliation MCP PoC?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Rathbones Reconciliation MCP PoC compare MyRathbones Portal across Orbus and ServiceNow" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Rathbones Reconciliation MCP PoC

by jjayaprarathbones

Overview Schema Related Servers Score Discussions

Python

Hybrid

Rathbones Reconciliation MCP PoC — Orbus Infinity + ServiceNow CMDB Emulator

A single deployed service exposing two MCP endpoints that emulate Orbus Infinity and ServiceNow CMDB on top of the same synthetic dataset. Built specifically to support the Current State Architecture Reconciliation Agent intern project.

⚠️ Synthetic data only. Do not load real Rathbones data into this repository. All object IDs, names, owners and attributes are invented to illustrate reconciliation patterns.

Why two MCPs?

The reconciliation agent's job is to compare two sources of truth:

Source	Models	Strength	Weakness
Orbus Infinity	Architectural lens — applications, components, relationships, capabilities, processes, HLD links	Best place for architectural relationships and design context	Naming and lifecycle data may drift
ServiceNow CMDB	Operational lens — production CIs, owners, lifecycle, dependencies	Authoritative for "what is actually deployed"	Doesn't carry rich relationship modelling

Treating each source as its own MCP server is intentional: it mirrors the production architecture (where each system would be its own Copilot Studio custom connector / MCP connection), and it lets the reconciliation agent reason about source-of-truth precedence per attribute.

Related MCP server: Constructoo MCP Server

Architecture

                           ┌─────────────────────────────────────┐
                           │       Render.com (one service)      │
                           │                                     │
   Copilot Studio          │  ┌──────────────────────────────┐   │
   Reconciliation   ──────►│  │  /orbus/mcp                  │───┼─┐
   Agent                   │  │  Orbus Infinity emulator     │   │ │
                           │  │  - list_object_types         │   │ │
                           │  │  - list_objects              │   │ │
                           │  │  - get_object                │   │ │
                           │  │  - search_objects            │   │ │
                           │  │  - get_relationships         │   │ │
                           │  │  - get_attribute_schema      │   │ │
                           │  │  - get_linked_documents      │   │ │
                           │  │  - find_servicenow_match     │   │ │
                           │  └──────────────────────────────┘   │ │
                           │                                     │ │
                           │  ┌──────────────────────────────┐   │ │
                           │  │  /servicenow/mcp             │───┼─┤
                           │  │  ServiceNow CMDB emulator    │   │ │
                           │  │  - list_classes              │   │ │
                           │  │  - query_cis                 │   │ │
                           │  │  - get_ci                    │   │ │
                           │  │  - get_ci_relationships      │   │ │
                           │  │  - get_user                  │   │ │
                           │  │  - search_business_apps      │   │ │
                           │  │  - get_class_schema          │   │ │
                           │  │  - find_orbus_match          │   │ │
                           │  └──────────────────────────────┘   │ │
                           │                                     │ │
                           │  ┌──────────────────────────────┐   │ │
                           │  │  Shared synthetic dataset    │◄──┘ │
                           │  │  (data/*.py)                 │     │
                           │  │  + reconciliation_truth.py   │     │
                           │  └──────────────────────────────┘     │
                           └─────────────────────────────────────┘

The reconciliation findings baked into the dataset

These are the 10 deliberate mismatches the agent should be able to surface. See data/reconciliation_truth.py for the full answer key.

#	Finding	Type	Orbus	ServiceNow
F1	MyRathbones Portal — clean match	`perfect_match`	`orb-app-001`	`sn-ci-001`
F2	ExBO vs Eximius Backoffice	`name_mismatch`	`orb-app-002`	`sn-ci-002`
F3	3 Orbus components vs 1 SN business app	`classification_mismatch`	`orb-comp-003a/b/c`	`sn-ci-003`
F4	CAMMS ERM approved, not yet in CMDB	`missing_in_servicenow`	`orb-app-005`	—
F5	Snowflake EDP — owner conflict	`attribute_conflict`	`orb-app-006`	`sn-ci-006`
F6	Citrix VDI — Live in Orbus, Retired in SN	`lifecycle_drift`	`orb-app-007`	`sn-ci-007`
F7	Proactis vs Proactis P2P — no ID link	`ambiguous_match`	`orb-app-009`	`sn-ci-009`
F8	Power BI — two SN candidates	`ambiguous_name`	`orb-app-010`	`sn-ci-010a`, `sn-ci-010b`
F9	ExBO→Snowflake feed missing in CMDB	`relationship_asymmetry`	`orb-int-100`	—
F10	Legacy Citrix Reporting only in SN	`missing_in_orbus`	—	`sn-ci-004`

Quick start

1. Push to your GitHub repo

The repo should sit on a personal account (not a Rathbones-managed account).

git init
git add .
git commit -m "Initial dual-MCP reconciliation PoC"
git remote add origin https://github.com/<your-user>/<repo-name>.git
git push -u origin main

2. Deploy on Render

New Web Service → connect the repo → Free plan.
Build command: pip install -r requirements.txt
Start command: python main.py
Render assigns a $PORT automatically; main.py reads it.

Once live you'll get a URL like https://<service>.onrender.com.

3. Wake the server (free tier sleeps after 15 min idle)

Open in a browser:

https://<service>.onrender.com/

You'll see a JSON response listing the two endpoints — server is alive.

4. Connect to Copilot Studio

In Copilot Studio → your agent → Tools → Add a tool → New tool → Model Context Protocol. Add each endpoint as a separate MCP connection:

Name	Server URL	Auth
`Orbus Infinity`	`https://<service>.onrender.com/orbus/mcp`	None
`ServiceNow CMDB`	`https://<service>.onrender.com/servicenow/mcp`	None

The agent will see 16 tools total (8 per server) and can route calls to whichever source it needs.

Project structure

rathbones-reconciliation-mcp/
├── data/
│   ├── orbus_metamodel.py         # Object types + attribute schemas
│   ├── orbus_objects.py           # ~14 synthetic Orbus objects
│   ├── orbus_relationships.py     # ~14 relationships
│   ├── snow_schemas.py            # CMDB class definitions
│   ├── snow_users.py              # 6 sys_user records
│   ├── snow_cis.py                # ~11 CIs paired with Orbus objects
│   ├── snow_rel_ci.py             # 8 cmdb_rel_ci entries
│   └── reconciliation_truth.py    # ANSWER KEY: 10 expected findings
├── tools/
│   ├── orbus_tools.py             # Pure Orbus query functions
│   ├── snow_tools.py              # Pure ServiceNow query functions
│   └── cross_lookup.py            # Bridge tool — Orbus <-> SN
├── servers/
│   ├── orbus_server.py            # FastMCP wrapper for Orbus tools
│   └── snow_server.py             # FastMCP wrapper for ServiceNow tools
├── main.py                        # Starlette app mounting both MCPs
├── requirements.txt
├── runtime.txt                    # python-3.11.0
└── README.md

Upgrade path to real data

When real OrbusInfinity and ServiceNow access is wired up, only the files in data/ need to be replaced. The tool functions, MCP wrappers and reconciliation agent never change.

Orbus: replace ORBUS_OBJECTS / ORBUS_RELATIONSHIPS with httpx GETs against https://rathbones-api.iserver365.com/odata/Objects and /odata/Relationships (OAuth2 implicit flow as per the OrbusInfinity HLD).
ServiceNow: replace SN_CIS / SN_REL_CI / SN_USERS with calls to https://rathbones.service-now.com/api/now/table/cmdb_ci_business_app, cmdb_rel_ci, sys_user (basic auth via a Rathbones service account).
Tool signatures stay identical. Function bodies just swap their data source. The agent calling the MCP server can't tell the difference.

Local development

python -m venv .venv
.\.venv\Scripts\Activate.ps1     # Windows PowerShell
# source .venv/bin/activate         # macOS / Linux

pip install -r requirements.txt
python main.py

Then in another shell:

curl http://localhost:8000/

Returns the endpoint list. To talk MCP, point an MCP client at http://localhost:8000/orbus/mcp or http://localhost:8000/servicenow/mcp.

Important notes

Synthetic data only. Do not load real Rathbones HLD, CMDB or owner data into any file in data/.
The MCP server is unauthenticated by design (synthetic data only). When the real-data version is built, authentication MUST be added before exposing it publicly.
Tenant DLP can block custom MCP server URLs in Copilot Studio. If the connection fails with "Couldn't load MCP tools", confirm with IT that Render.com URLs are allowed.
The reconciliation answer key in data/reconciliation_truth.py is for validating the reconciliation agent — it is not exposed via either MCP server.

This server cannot be installed

license - not found

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

–Release cycle

–Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
open source
OpenAI
Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security

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/jjayaprarathbones/reconciliationTestMCP'

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