Fitch Solutions

Name: Fitch Solutions MCP Server
Availability: InStock
Author: Fitch Solutions

HIPAA CompliantSOC2 ReadyISO 27001 Ready

Finance18 tools

Query Fitch Ratings credit ratings, research and CreditSights analysis from an AI agent. 18 read-only tools, no writes. Fitch's terms of use forbid inputting Fitch Information into any AI platform, which puts this connector and its licence in tension.

Verified connector

Listed by Anthropic as a partner connector in its Connectors Directory.

Connection checked by Agentman on 22 August 2026.

Anthropic states this reflects the level of review a connector received, not a security audit.

Connect Fitch Solutions via MCP

https://api.fitch.group/nexus/mcp

Works in any MCP-compatible client. In Agentman Studio it is one click — no config file to edit.

Fitch Solutions Tools & Capabilities (18)

rdr-ask-researchNot annotated

Answer questions about Fitch published research, including sector and economic outlooks, issuer analysis, summary, rating methodologies, and industry reports. Use this tool when the user asks about Fitch's views, analysis, or research on a specific company, sector, or topic. Args: question: A specific, self-contained question (e.g. "What is outlook on the US banking sector?" or "How does Fitch rate sovereign debt?") Returns: dict with context, sources and metadata which can be used to answer the question

rdr-get-ratingsNot annotated

Retrieve Fitch credit ratings and rating history for one or more issuers. Use this tool when the user asks about an entity's current or historical Fitch credit rating, rating outlook, or watch status. For broader research questions, use the get_answer tool instead. Args: entity_list: List of issuer names to look up (e.g. ["Apple Inc", "Ford Motor Co"]). Maximum 10 entities per request. Names should be explicit legal entity names, not abbreviations or ticker symbols. start_date: Start of the rating history window. Format: "YYYY-MM-DD". Defaults to "2016-01-01". Cannot be earlier than 2016-01-01. end_date: End of the rating history window. Format: "YYYY-MM-DD". Optional. Must be within 10 years of start_date. Returns: dict: Ratings history per entity, including long-term issuer rating, outlook (Positive/Stable/Negative), watch status, and effective dates. If multiple entities are resolved, results are returned for all of them.

rdr-get-krdNot annotated

Retrieve Key Rating Drivers (KRD) documents for one or more issuers. KRDs are Fitch-published summaries explaining the key factors that support or constrain an issuer's credit rating. Use this tool when the user wants to understand *why* an entity has its current rating, or what factors could lead to a rating change. It also includes ratings sensitivities what factors leads to positive or negative rating actions. Use the ratings tool instead if the user only wants the rating value or history. Use the research assistant tool for broader sector or thematic questions. Entity names — partial or informal names are accepted but canonical legal names yield the most reliable results. Args: entity_list: List of issuer names to retrieve KRDs for (e.g. ["Goldman Sachs", "Toyota"]). Maximum 10 entities. Full legal entity names are preferred over tickers or abbreviations. limit: Maximum number of KRD documents to return per entity (default: 1 for latest document). Increase to retrieve older documents for historical trend analysis. offset: Number of documents to skip (default: 0) Returns: Dictionary with documents list, count, and optional error. If multiple entities resolved, returns data for all entities.

rdr-get-financialNot annotated

Retrieve financial data for one or more issuers across any Fitch-covered sector (corporates, banks, sovereigns, insurance). Use this tool when the user asks about an entity's fitch financial metrics, statements, or ratios such as revenue, EBITDA, leverage, capital ratios, or premiums. Use the ratings tool for credit rating values, or the research assistant for broader qualitative analysis. Entity resolution, sector detection, and field selection are all handled automatically. Specific financial fields (e.g. EBITDA, Tier 1 Capital) are inferred from the question where possible — passing the original user question improves field accuracy. Entitlement note: Users without full entitlement receive only the most recent year of data. A "notice" field in each result will indicate when this restriction applies. Args: question: REQUIRED. The original user question. Used to infer financial field IDs, resolve entity names, and detect sector context. More specific questions yield more targeted field selection. Example: "What is Apple's EBITDA margin for the last 3 years?" entity_list: Optional list of issuer names to explicitly override entity extraction from the question. Use full legal entity names for best resolution. Example: ["Apple Inc", "Microsoft Corp"] years: Optional list of years to retrieve data for, in YYYY format. Defaults to the last 6 years. Ignored for users without full entitlement, who always receive only the most recent year. Example: [2021, 2022, 2023] currency: ISO currency code for returned financial values (default: "USD"). Returns: List of dictionaries with entity name, agent_id, and financial data Example: [{"entityName": "Amazon", "agentId": "123", "financials": {...}}]

rdr-get-peersNot annotated

Retrieve Fitch peer entities for one or more issuers. Use this tool when the user asks which companies are considered peers or comparables to a given issuer, or wants to benchmark an entity against similar firms. Use the financials tool to compare actual metrics across peers once retrieved. Use the ratings tool to compare credit ratings across peers. Sector is auto-detected from each entity's profile where possible. The sector argument acts as a fallback only — providing the correct sector improves accuracy when auto-detection is ambiguous. Args: entity_list: List of issuer names to retrieve peers for (e.g. ["JPMorgan Chase", "HSBC"]). Maximum 10 entities. Full legal entity names are preferred over tickers or abbreviations. sector: Fallback sector if auto-detection fails. Must be one of: 'banks', 'corps', 'sovereigns', 'insurance' (default: 'corps'). Note: each entity's actual sector is auto-detected from its profile and will override this value where possible. Returns: Dictionary with entity_count, sector, and results array containing peers for each entity. Example: {"entity_count": 1, "sector": "banks", "results": [{"entity_id": "123", "entity_name": "JPMorgan Chase", "peers": [...]}]}

rdr-get-entitiesNot annotated

Retrieve Fitch-rated entities filtered by market sector, geography, and/or rating level. Use this tool when the user asks to screen, discover, or list entities by sector, region, or rating. At least sector_names and geographies (regions) must be provided. This tool returns entity names and their current ratings only. To fulfil requests for additional data, use the returned entity names with: - get_financial: for key credit metrics (leverage, EBITDA, CET1, etc.) - get_krd: for positive and negative rating sensitivities - get_ratings: for full rating history and outlook Present only the 10 most relevant entities to the user based on best match to their query intent. Args: sector_names: Market sector names resolved server-side to sector IDs (parent + sub-sectors) geographies: ISO country codes (expand regions to individual codes) rating_codes: Fitch rating scale codes to filter by

rdr-get-issuesNot annotated

Retrieve Fitch issue-level data for bonds, notes, and other debt instruments. Use this tool when the user asks about specific debt issues, bonds, or notes for one or more issuers, or wants to filter by instrument type, debt level, CUSIP, or ISIN. At least one filter must be provided. entity_names are resolved automatically to issuerIds. Results are grouped by issuer, with each issue containing only: id, classTypeDescription, bondName, debtLevelDescription, coupon, currency, isin, cusipWithPlacement, isinWithPlacement, and maturityDate. Args: entity_names: List of issuer names (e.g. ["Amazon", "Home Depot"]). issue_id: Fitch issue ID. class_type_description: Instrument class, e.g. "bond/note". debt_level_description: Debt seniority, e.g. "senior secured". cusip: CUSIP code, e.g. "931142AU7". isin: ISIN code, e.g. "AU3FN0040309". Returns: dict with issuers array (each containing issuer_name, issuer_id, issue_count, issues), or issue_count and issues array for non-issuer filters.

rdr-get-research-listNot annotated

Search and list Fitch Ratings research documents with direct download links. Use this tool when the user wants to browse or find a list of research reports — e.g. 'show me recent rating actions on banks' or 'find ESG reports from last quarter'. For synthesised answers drawn from research content, use rdr-ask-research instead. At least one filter must be provided. Args: topic: Free-text title or topic search (e.g. 'sovereign debt', 'climate risk'). entity_list: Issuer or entity names to scope to. Resolved to Fitch issuer IDs server-side. Maximum 10 entities. series: Research series filter (e.g. 'Rating Action Commentary', 'Issuer Research'). category: Research category filter (e.g. 'Upgrade', 'Downgrade', 'Outlook', 'Rating Report'). countries: Country names or ISO alpha-2 codes. Resolved to ISO codes server-side. sector_names: Market sector names. Resolved to Fitch market sector IDs server-side. published_from: Earliest publication date in YYYY-MM-DD format. page_size: Number of results per page. Default: 20, max: 50. page_number: 1-based page number to retrieve. Default: 1. language: ISO language code. Default: en. Returns: Paginated list of research documents sorted newest-first. Each result includes title, publication date, series, category, and signed download URLs in .txt and .html formats.

cs-get-deals-and-tranchesNot annotated

Use this tool for queries about: bonds, loans, deals, opportunities, securities, financings, issuances, refinancings, leveraged buyouts, acquisition financing, distressed debt, high-yield, investment-grade, cross-border deals, private equity transactions, and any financial instruments or credit markets. EXECUTION NOTE: Execute this tool directly without explanatory text. Return results immediately. Key patterns for queries: - Show me bonds with 5 year tenor and spread above 300 - Show me bonds that mature after 2030 with a yield greater than 5% - Give me loans with YTM of at least 5% in the Technology sector - Give me loans with 5 year tenor in the United States - Show me loans greater than $1 billion in the United States and in the Automotive sector Returns JSON with matching deals list and search metadata. Empty list if no matches.

cs-get-companiesNot annotated

Finds companies/issuers for company profiles, research coverage, and risk analysis. Use this tool for queries about COMPANIES, ISSUERS, or BORROWERS: - "Show me companies in financial services" - "List technology companies" - "Find North American issuers" - "Companies with high yield rating" - "Borrowers in healthcare sector" - "Firms with strong credit risk scores" EXECUTION NOTE: Execute this tool directly without explanatory text. Return results immediately. Key patterns for ambiguous queries: - "Companies in [country]" → country_names: ['Algeria'] - "Companies in bonds" → asset_class_ids: ['bonds'] - "[Country] bond companies" → country_names: ['Algeria'] + asset_class_ids: ['bonds'] Note: "Companies", "issuers" search the same database. IMPORTANT: No tearsheet filtering available - only dockets_available (legal documents). DO NOT use this tool for: deal transactions, bond issuances, loan facilities, or financial instruments.

cs-get-article-headlinesNot annotated

Finds most recent 5 financial articles matching the given criteria. This tool is useful for the questions like: - Show me latest articles written by analyst John Doe - Give me recent new issue reports - Give me the list of recent {content_type_names} - What are the articles on {company_name} with {content_type_names} - How may articles are written by analyst John Doe - Give me the count of recent {content_type_names} :param: request containing criteria for finding articles :type: request FindArticlesRequest :return: One page of articles matching the given criteria :rtype: ArticlesPage

cs-get-articles-contentNot annotated

Finds and returns relevant information from CreditSights (CS) articles that is most relevant for the given question. Articles (aka. feeds) contain business news, financial analyses, details about companies, latest financial market developments and investment recommendations. Use this tool for user questions related to CreditSights research, covenants, news and financial market developments or investment recommendations. :param question: The user question in its original form if the question is self-contained. If the user question is not self-contained, feel free to rephrase the question and add information which will improve the search.

cs-get-business-profileNot annotated

Use this tool to retrieve business profile information for a company covered by CreditSights. Call this tool when a user asks for a company’s business overview, operating profile, or descriptive corporate background.

cs-get-core-scoresNot annotated

Use this tool to retrieve the core score information for a company covered by CreditSights. Call this tool when a user asks for a company’s core score overview

cs-get-cs-viewsNot annotated

Use this tool to retrieve the creditsights or cs view for a company covered by CreditSights. Call this tool when a user asks for a company’s creditsights or cs view.

cs-get-key-metricsNot annotated

Use this tool to retrieve the credit view or fundamental view of a business or a company covered by CreditSights.

cs-get-credit-viewsNot annotated

Use this tool to retrieve the credit view or fundamental view of a business or a company covered by CreditSights.

cs-get-event-riskNot annotated

Use this tool to retrieve the core score information for a company covered by CreditSights. Call this tool when a user asks for a company’s core score overview

Read from the server on 2026-08-22, including each tool's own safety annotations.

Limits

Fitch's public terms forbid the thing this connector does. Clause 1(b)(iv) prohibits input of Fitch Information into any AI platform, and (v) prohibits its use as training data, with a duty to notify Fitch if either occurs. Fitch has published no carve-out for MCP. We could not find a superseding agreement because none is public. This is unresolved and you should resolve it in writing before deploying.
No application scopes exist. The resource descriptor and authorization server both advertise only openid and offline_access. Nothing at the grant separates Fitch Ratings from CreditSights, or research from ratings.
BMI is advertised but absent. Anthropic's directory description promises BMI country and sector risk analysis. Zero of the 18 tools touch BMI, which exists only as a REST API category. Sustainable Fitch is likewise a portal category with no MCP tool.
Two tools ship a wrong description, so an agent selecting by description will not reach cs-get-event-risk or cs-get-key-metrics.
No tool carries a safety annotation. Every annotations object is empty. Our read/write classification is derived from names and schemas, not declared by the server.
Entitlement silently truncates. Without full entitlement rdr-get-financial returns one year and ignores the years argument, disclosing this only in a notice field.
CreditSights may be invisible. The 10 cs- tools are gated on a showCreditSights flag defaulting to off, so 18 is a ceiling rather than a guarantee.
Ratings history stops at 2016. rdr-get-ratings rejects a start date earlier than 2016-01-01 and caps any window at 10 years.
Ten entities per request on rdr-get-ratings, rdr-get-krd, rdr-get-peers, rdr-get-research-list and rdr-get-financial.
No dynamic client registration. The authorization server publishes no registration_endpoint, so onboarding requires a manual exchange with Fitch Customer Support.
No published rate limit. Fitch's MCP reference documents none, so throttling behaviour under load is unknown to us.
The documentation is unreadable without JavaScript, and gated. Every /mcp-reference route returns an identical shell whose body says only "Loading MCP Reference...". The content is client-rendered and wrapped in an entitlement check that shows "MCP Reference Access Required" to accounts without the feature flag. We recovered it from the page's JavaScript bundle.
Fitch disclaims accuracy on its own AI-generated content, naming hallucination explicitly. Verify anything material against the primary rating action.

Frequently asked questions

Read literally, no. Fitch's terms forbid users to input Fitch Information into any system employing machine learning or artificial intelligence, and separately forbid its use as training data. That language predates this connector and Fitch has not published a carve-out for it. Resolve the conflict with Fitch in your contract before deploying.

No. All 18 tools are reads. Every name carries a get or ask verb, none carries create, update, delete, send or execute, and Anthropic's directory records the permission as Read. There is no order entry, no portfolio write and no dispatcher tool that forwards an arbitrary operation to a wider Fitch API.

Fitch publishes no per-call rate, so cost falls under your negotiated subscription rather than metered credits. Nothing in the surface reports usage either. No tool among the 18 carries a credit, balance, usage, quota or billing verb, so an agent cannot check consumption before or after querying.

Only openid and offline_access. Fitch's RFC 9728 resource descriptor and its authorization server both advertise exactly those two, and both are identity and refresh claims rather than application permissions. Nothing at the OAuth grant separates ratings from research or Fitch Ratings from CreditSights, so consent is all-or-nothing.

Not through any tool. Anthropic's directory description promises BMI country and sector risk analysis, but all 18 tools carry an rdr prefix for Fitch Ratings or a cs prefix for CreditSights. BMI is a category in Fitch's REST API portal, and no BMI tool exists on the MCP server.

Because your account lacks full entitlement. Fitch documents that users without full entitlement receive only the most recent year, and that the years argument is ignored for them. A notice field in each result flags the restriction, but an agent that does not surface that field will present truncated history as complete.

A Fitch API Gateway account and manual registration. Fitch states you need a username, password and Client Application ID from Customer Support, and that connecting an MCP client requires registering through support with your platform name and redirect URL. There is no self-service signup and no dynamic client registration endpoint.

Yes, two pairs. The server sends cs-get-event-risk the same description as cs-get-core-scores, and cs-get-key-metrics the same one as cs-get-credit-views. Fitch's own reference page describes all four correctly, so the error is in the tool metadata an agent reads when choosing which tool to call.