MCP-native valuation for RIAs and wealth practices: one seven-method engine, two lanes. Sellers get fair value, an asking price, a low/high range and data confidence; buyers get a private walk-away ceiling, CRD-based target screening and an acquisition pipeline. Claude or another MCP-compatible assistant gathers sourced figures from CRM, ledger and custodian systems, then surfaces gaps and disagreements before valuation. Deal Room supports private buyer/seller rehearsals and invitation-only shared discussions, with a free simulated example. A2A-compatible enterprise agents can request and prepare target information through the same human-approved broker, without sharing either side's private valuation.
practice valuationsell-sidebuy-sidem&aacquisition screeningdue diligenceform advbenchmarksdeal roomsa2amcp-native
Combines other servers' capabilities to reach an outcome. Orchestrates data and domain servers into a finished decision, not just a data point. More on Composition servers →All seven roles →
Vendor-documented: reviewed the September 30 through October 23, 2026 releases, including v1.0.21, and the current developer reference. The vendor documents 17 tools, engine 1.8.0 and server 1.20.0; valuation accuracy, permission enforcement and workflow outcomes were not independently verified. Sources: https://valuationmcp.ai/release-notes and https://valuationmcp.ai/developers.
Requires an account and OAuth 2.1; tools run against the signed-in user's data. This is not read-only: tools save practice inputs and provenance, compute and store valuations, generate rehearsal memos, and create or submit data requests. The agent gathers figures through separately connected source servers; catalog support is not an independently tested integration guarantee. Reconnect existing clients to load the expanded tool list.
Modeled planning and diligence estimates, not a formal appraisal, executable offer, investment recommendation or endorsement. Filed regulatory AUM and client counts are not current financial statements or household counts. Buy-side screening can derive revenue from published retail-practice medians; derived estimates and target-provided figures remain distinct from verified financials. Non-retail targets without supplied revenue are not screened. Missing inputs and flagged placeholders lower confidence; compare saved runs only with attention to engine and benchmark versions.
Vendor-positioned Deal Room: seller preparation anticipates buyer objections; buyer preparation tests the seller's case. Private memos stay private. Seller-hosted rooms share selected figures with range and coverage; buyer-hosted rooms share target facts and diligence needs, never the buyer's ceiling, fair value, range, method values or quality scores. The free, account-free example is a simulation using public ADV data and median-filled revenue/profit estimates, not a live negotiation or evidence that a firm is for sale. Saved memos, invitations and comment threads belong to the full app. Source: https://valuationmcp.ai/deal-room-demo.
Vendor-described sharing controls: requests require a preview and explicit owner approval; direct firm inbox delivery requires a verified CRD claim and opt-in. New requests are NDA-gated until an executed document is uploaded and acknowledged by the counterparty, or the target waives the gate. Existing open requests remain ungated and deal rooms show NDA status without enforcing that gate. No assistant signs an NDA, and the built-in draft template remains pending counsel review. Buyer walk-away ceilings and the firm's own valuation are not shared through the request flow.
A2A is an alternative authenticated transport for the information-request broker, not open access to another firm's systems or autonomous negotiation. The buyer approves creation and the firm owner approves the answer; accepted figures become target-provided inputs. A verified CRD claim checks the account's connection to a filed firm profile, not ownership or financial accuracy. Agent-reported sources and saved-record matches are not audits. A2A 1.0 uses the same OAuth permissions as MCP; streaming and push notifications are not supported. Sources: https://valuationmcp.ai/agent-to-agent and https://valuationmcp.ai/.well-known/agent-card.json.
Hosted use stores practice inputs, provenance, valuation outputs and deal-room content; it is not a local-only calculator. Archiving retains records, and no fixed account-deletion deadline is published. The vendor says the service is not designed or contracted to hold client nonpublic personal information; do not submit client NPI, including in free-text notes. Review firm authorization, counterparties, AI-provider handling and retention before connecting records or sharing a room. Vendor privacy statements are not an independent security audit: https://valuationmcp.ai/privacy.
Advertised plan restrictions apply: the vendor's October 23 release documents one practice and one full valuation on Free, with later reruns limited to headline, range and coverage. Buy-side work, data requests and saved deal-room rehearsal require Deal; the separate public simulated example is free. The reviewed pricing page labels preview payments as test mode; production billing was not verified. Check current entitlements and pricing rather than assuming every documented tool or skill is available: https://valuationmcp.ai/pricing.
Start with read-only scopes and keep client-side approval prompts on until the connection is proven.
Rate this server
How to connect ValuationMCP
Step 1
Remote server: paste a URL
ValuationMCP publishes a remote (Streamable HTTP) endpoint, so nothing is installed locally. Add it as a custom connector in Claude, ChatGPT or your IDE and paste the endpoint below.
Your client opens a browser sign-in with the vendor. Approve only the scopes you need, and use a read-only account first when the platform offers one.
Step 3
Verify, then widen access
Restart your client, confirm the server's tools appear, and run one read-only question first. Keep client-side approval prompts on for any tool that can write, trade or send. Confirm with your firm's compliance policy before connecting systems holding client data.
Read-only, in three passes. First gather my practice's own figures: households, AUM, recurring vs. one-time revenue, fee mix, client age distribution and top-10 concentration from CRM and custody, and revenue, expenses, owner compensation and margin from the accounting system, recording where each figure came from and marking anything you could not source rather than estimating it. Second, run HnyComb's Value my practice skill on those inputs, keeping the source note attached to every figure, and show the seven-method blend, the range and the data confidence behind it; then run its Reconcile the Numbers skill to check the figures against filed data and published medians and name each gap. Third, pull the filed peer distribution for my state and AUM band from ADVmcp and use HnyComb's Benchmark Against Cohort skill to place my result against firms like mine. Output the valuation range, the inputs table with sources, the reconciliation gaps, and where the practice sits against filed peers. No client names or account numbers anywhere in the output, and do not write, export or share anything.
Guardrail · Read-only, no client identities in the output. The valuation is a modeled estimate, not an appraisal, and peer percentiles are positions rather than grades: Form ADV carries no revenue, EBITDA or margin figures, so peer data contextualises the number and never moves it.
Read-only. Start by writing my acquisition thesis back to me in one paragraph, geography, AUM band, client mix, custodian, succession situation, and ask about anything I left ambiguous before you search. Then run HnyComb's Find and screen acquisition targets skill: ADVmcp finds candidate advisers from filed Form ADV data and HnyComb puts a low-confidence walk-away number on each, returning a ranked shortlist with the filed facts behind every match. For the one target I name, run the Buy-Side Ceiling skill to produce a defensible ceiling, using target-supplied figures where I have them and labelling every private figure I do not have as a named assumption with the effect it has on the ceiling; if I name two targets, use Compare Targets to read them side by side without picking a winner. State the confidence level and what would raise it. Do not contact, email or approach anyone, and do not draft outreach.
Guardrail · Nothing in a public filing indicates a firm wants to sell. A shortlist is research, never a recommendation to approach or offer. Private figures are either target-supplied or a named assumption, and confidence on public data alone will be low. That is the honest result, not a defect.
Compliance history and diligence file
The regulatory record a buyer's counsel will request.
Read-only: assemble my firm's regulatory record from two directions, my internal compliance or GRC systems for what they actually hold (policy versions, control testing, vendor diligence, open findings and remediation status) and the public regulatory and firm-intelligence sources for registration history, ADV disclosures and complaints. Show them side by side and flag anything disclosed publicly with no internal record, or internally tracked that the public record does not reflect. List exam findings and correspondence separately as 'to gather offline' unless a connected system genuinely holds them. Cite each source and mark anything unverified as 'to confirm'. Do not file, submit or amend anything.
Guardrail · Read-only. The internal half of this record usually lives outside any connected tool, and filings are amended through official channels only.