MCP
TRUE's Model Context Protocol server — one endpoint, one auth flow, every tool TRUE uses internally, available to any MCP-compatible client.
TRUE’s MCP server is the most direct integration path available. Every data tool the TRUE platform uses internally — prices, news, on-chain intelligence, user context — is exposed through a single Model Context Protocol endpoint that any MCP-compatible AI client can connect to in minutes. No secondary API, no reduced feature set: external clients and internal agents operate on exactly the same surface.
What it is
The TRUE MCP server implements the open Model Context Protocol standard over HTTP. It accepts standard MCP tool-call requests, authenticates them against TRUE’s token layer, executes the requested tool against live data, and returns structured results. The server is stateless per request; session continuity is the client’s responsibility. Because the MCP surface is identical to what TRUE’s own agent system uses, responses carry the same data quality, latency characteristics, and error semantics that power every TRUE chat answer.
Who it’s for
- Developers building AI-native applications that need reliable, real-time financial data without managing their own data pipelines.
- Partners embedding TRUE intelligence inside research desks, trading dashboards, or white-label AI products.
- Power users extending Claude Desktop, Cursor, or any MCP-compatible editor to answer financial questions using TRUE’s live data.
How it works
Connecting
Point any MCP-compatible client at the TRUE MCP endpoint and authenticate with a TRUE bearer token. The transport is standard HTTP; no WebSocket, no SDK install required. The full tool catalog is discoverable via the standard MCP tools/list call immediately after connection.
Authentication flow
Static bearer tokens are the fastest path. Generate a scoped key from the TRUE dashboard, add it as a Bearer header, and the connection is live. Tokens come in two classes:
tp_live_...— production-tier keys scoped to the tools you specify at issuance. Use the narrowest scope that still covers your use case.tp_test_...— sandbox-tier keys backed by non-production fixtures. No real data, no real points, safe for integration testing.
OAuth is the right choice for multi-user deployments — a research workspace shared across a team, or a consumer product built on top of TRUE. The OAuth grant binds an MCP session to a specific TRUE user, inheriting that user’s watchlist, points balance, and permission scope. The full redirect flow, PKCE requirements, and token refresh cycle are documented on the Authentication page.
Making a tool call
Every call follows the standard MCP protocol shape: a method of tools/call, a name matching one of the catalog entries, and an arguments object. The server validates the argument schema, checks the token’s scope against the requested tool, executes the tool against live data, and returns a structured result. If upstream data is unavailable, the server returns a structured error — never a hallucinated payload.
Connecting from Claude Desktop
Point Claude Desktop at the MCP endpoint above with a TRUE bearer token as the authorization header. After restarting Claude Desktop, the TRUE tools appear under the MCP tools menu and are callable from any conversation. Setup takes under two minutes.
Connecting from Cursor or Continue
Both editors accept the same MCP server configuration shape as Claude Desktop. Add the TRUE server entry to your editor’s MCP configuration and restart. The tools are immediately available to the in-editor assistant.
The MCP server uses standard HTTP transport and accepts the MCP tools/call wire format. Clients connect by pointing at the TRUE MCP endpoint with a scoped bearer token as the authorization header. Full connection details, token issuance, and the complete tool catalog with required scopes are in the Authentication and Partner Integration docs.
Available tools
The MCP catalog mirrors the tools available to TRUE’s internal agent system. Every tool below is callable from external clients with the appropriate scope.
get_price
Latest price, 24h change, volume, and market data for one or many assets across crypto, stocks, and tokenized equities.
search_assets
Resolve symbols and names across all asset classes TRUE supports, returning canonical identifiers.
getMemecoinOverview
Canonical overview of any Solana long-tail token: FDV, liquidity, holder count, social signals.
getMemecoinSecurity
Mint authority status, freeze authority status, holder concentration, and risk flags for any Solana token.
getMemecoinHolders
Top holders ranked by balance, with concentration warnings where applicable.
getMemecoinTrades
Most recent on-chain trades for any Solana token, with timestamps and amounts.
getMemecoinChart
OHLCV candles at the requested timeframe for any Solana token.
get_news
Latest headlines across crypto and macro, including AI-generated sentiment scores.
get_watchlist
The authenticated TRUE user’s saved assets, returned in full with current prices.
get_points_balance
Points balance, streak, rolling-window earned, and referral stats for the authenticated user.
get_highlight_poll
Fetch the Polling Pulse giveaway poll attached to a TRUE Highlights post, including your vote status and live results.
vote_highlight_poll
Cast a vote on a TRUE Highlights Polling Pulse poll. Requires a linked wallet; one vote per wallet per poll.
Admin MCP (requires @true.trading)
Admin tools live on a separate MCP endpoint: /api/v1/mcp/admin. This endpoint is not reachable by regular user accounts — only @true.trading OAuth identities and admin-flagged true_sk_ keys are admitted. A non-admin authenticated caller receives a 403; an unauthenticated caller receives a 401.
To add the admin MCP as a connector in Claude or ChatGPT, point it at /api/v1/mcp/admin instead of /api/v1/mcp and authenticate with a @true.trading OAuth session or an admin key. The two connectors are fully independent — connecting one does not affect the other.
Admin tools are not listed or callable on the user MCP endpoint (/api/v1/mcp), even for @true.trading accounts. They are only discoverable and executable on the dedicated admin endpoint. This is enforced at the server level, not by a runtime flag.
admin_lookup_wallet
Look up a user’s profile and TRUE Points balance by wallet address.
admin_points_adjust
Add or deduct TRUE Points from a wallet with a mandatory reason string.
admin_list_highlights
List all TRUE Highlights with status, expiry, and live/inactive visibility.
admin_upsert_highlight
Create a new highlight or update an existing one. Full localization support.
admin_disable_highlight
Deactivate a highlight by ID (sets is_active=false).
admin_list_comments
List highlight comments with optional filters (highlight, status, user, cursor).
admin_moderate_comment
Set a comment to visible, hidden, or removed.
admin_ban_commenter
Ban a user from commenting across all highlights.
admin_unban_commenter
Lift a commenting ban and restore comment write access.
admin_set_highlight_poll
Attach or update a Polling Pulse giveaway poll on a highlight (2–4 options, points/SOL reward).
admin_get_highlight_poll_results
Get poll config and live vote results for any highlight.
admin_toggle_highlight_poll
Manually close a poll so no more votes are accepted.
admin_distribute_highlight_poll
Trigger immediate giveaway reward distribution for a closed poll.
admin_system_health
Get a comprehensive system health report covering upstreams, queues, cache, and the database.
The rules it enforces
- Scope enforcement. Every tool call is checked against the scope embedded in the token. A key without the
quotesscope cannot callget_price, regardless of the request payload. - Schema validation. Argument shapes are validated before execution. Malformed arguments return a structured validation error, not a silent failure.
- Per-turn tool budget. A single call cannot exhaust the rate-limit bucket; per-tool limits exist independently of the per-token limit.
- Rate limits. 100 requests per minute on the public tier, enforced per token. Bursts above the limit receive a
429with aRetry-Afterheader. - Tool versioning. Breaking changes to a tool’s argument or response shape ship as new tool names, never as mutations to an existing tool. Existing integrations are not silently broken.
- Structured errors only. When an upstream (prices, on-chain data) is unhealthy, the affected tool returns a structured error payload. The server never fills a gap with a synthesized or cached value that could be mistaken for live data.
100 requests per minute per token on the public tier. Higher quotas are available for partners — contact [email protected]. Per-tool limits and the full quota table are on Rate Limits.
Safety, security & trust
Never expose bearer tokens in client-side code. All MCP calls travel over TLS, but TLS does not prevent a token from being extracted from a JavaScript bundle or a mobile binary. Route MCP calls through your backend, mint short-lived tokens where possible, and revoke immediately on suspicion. Apply the principle of least privilege at key issuance — a tool a key cannot call cannot be abused with that key.
Token revocation is instant. A compromised key can be revoked from the TRUE dashboard and the revocation propagates across the MCP edge within seconds. There is no grace window; a revoked key is refused immediately.
Audit logging is on by default. Every tool call made against a token is logged with a timestamp, tool name, sanitized arguments, and a trace ID. Logs are available for review and are retained according to the compliance schedule documented on Compliance & Jurisdictions.
No write surface. The MCP server is read-only. No tool in the catalog can move funds, place orders, or modify user state. Execution actions flow through a separate, explicitly opt-in path described in Agentic Trading.
Sandbox parity. The tp_test_... tier runs against non-production fixtures that replicate the same schema and behavior as production. Test integrations behave the same way real integrations do — without touching live data or user accounts.
Why it’s well thought through
Symmetry between internal and external. TRUE’s own agent system and external MCP clients call the same tools against the same infrastructure. There is no second-class external API that receives stale or degraded data. This symmetry is a design constraint, not a marketing claim: any regression in the external surface is immediately visible in the product’s own chat.
Fail-fast semantics. The MCP server is designed to surface failures clearly rather than paper over them. A tool that cannot get live data returns an error the calling LLM can reason about — “prices are temporarily unavailable for this asset” — rather than a confident-looking but stale or fabricated response. This makes LLM applications built on the MCP more reliable, because the model receives a signal it can act on.
Narrow, composable tools. Each tool does exactly one thing. This keeps the context window cost per call low, the argument shapes simple, and the surface area for misuse small. Complex queries are composed by the calling LLM across multiple tools, not by a monolithic tool that over-fetches.
Versioning as a contract. Tool names are stable. When a tool’s behavior changes in a breaking way, a new tool name is published and the old name is kept for a deprecation window. Integrations are never silently broken by a server-side change.
White-label MCP setup is available on the partner tier. Partner accounts provision tokens for end users from a shared dashboard, brand the OAuth consent screen with custom copy and logo, and inherit the full tool surface with SLA guarantees. Revenue share, onboarding flow, and contractual terms are on Partner Integration.
Common questions
Can I use the MCP server without a TRUE account? No. Every MCP call requires a bearer token issued to a TRUE account. Creating an account is free; generating a scoped key takes under a minute from the dashboard.
Does the MCP server support streaming responses? Individual tool calls return synchronous JSON responses. Streaming is available on the Chat endpoint, which uses the MCP tools internally and exposes results as an SSE stream. Use Chat for conversational flows; use MCP for direct tool access.
What happens if a tool is unavailable?
The affected tool returns a structured error object with a machine-readable code, a human-readable message, and a retryable boolean. Permanent errors (bad arguments, scope denied) are not retryable; transient errors (upstream degraded) are. The calling LLM can route around the failure gracefully.
How do I know which scope to request for a given tool?
The tools/list response includes a requiredScopes field for each tool. Request only the scopes your integration actually uses. Smaller scope sets reduce the blast radius if a key is compromised.
Can the MCP server execute trades or move funds? No. The MCP surface is read-only. Execution requires an explicit user signature via the separate Agentic Trading path.
What is the latency profile? Most tool calls complete in under 300ms from the edge. On-chain tools (memecoin holder queries, Solana RPC calls) can take up to 1.5 seconds under load. Price tools backed by the TRUE Quotes layer are consistently sub-100ms.
How does the sandbox tier differ from production? Sandbox tokens receive fixture data — deterministic, realistic, but not live. Prices do not change; balances are synthetic. The response schema is identical to production, so sandbox integrations port to production without code changes.
Is there a webhook alternative to polling for price changes? Yes. The Webhooks surface delivers push notifications for price thresholds, signal transitions, and catalog changes. Use webhooks to avoid polling; use MCP tools for on-demand lookups.
Are MCP calls included in my points earning? MCP calls do not earn points. Points are earned through in-app actions — swaps, streaks, referrals — as documented on Points & Rewards.
How do I report a bug in a tool response?
Include the trace ID from the response header (X-Trace-Id) in a report to [email protected]. The trace ID links directly to the server-side execution log for the call.
Related features
- Agents — the internal agent system that calls MCP tools to answer chat questions.
- Authentication — OAuth, scoped keys, JWT, and token rotation.
- Rate Limits — per-tool and per-tier quotas in full.
- Webhooks — push delivery as an alternative to polling MCP tools.
- Agentic Trading — the execution surface that complements the MCP read layer.