# NY Fed SOFR, EFFR & OBFR Overnight Benchmark Reference Rates (remote · ceadigital.io)

Official Federal Reserve Bank of New York SOFR, EFFR, and OBFR overnight reference rates.

- Trust score: 79/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `ceadigital.io`: 79/100 (this document), [markdown](https://verifymcp.io/servers/io-ceadigital-nyfed-sofr-reference-rates/mcp-sofr.md), [page](https://verifymcp.io/servers/io-ceadigital-nyfed-sofr-reference-rates/mcp-sofr)

## Channel facts

- Endpoint: `https://ceadigital.io/mcp/sofr`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 2656 tokens (~94/item across 28 items; 28 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 53/100
  - Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 28 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 28 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### How do I install the NY Fed SOFR, EFFR & OBFR Overnight Benchmark Reference Rates MCP server?

NY Fed SOFR, EFFR & OBFR Overnight Benchmark Reference Rates is a hosted endpoint at https://ceadigital.io/mcp/sofr, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http io-ceadigital-nyfed-sofr-reference-rates 'https://ceadigital.io/mcp/sofr'
```

### Cursor

```json
{
  "mcpServers": {
    "io-ceadigital-nyfed-sofr-reference-rates": {
      "url": "https://ceadigital.io/mcp/sofr"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "io-ceadigital-nyfed-sofr-reference-rates": {
      "type": "http",
      "url": "https://ceadigital.io/mcp/sofr"
    }
  }
}
```

### Codex

```toml
[mcp_servers.io-ceadigital-nyfed-sofr-reference-rates]
url = "https://ceadigital.io/mcp/sofr"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-ceadigital-nyfed-sofr-reference-rates": {
      "type": "remote",
      "url": "https://ceadigital.io/mcp/sofr",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-ceadigital-nyfed-sofr-reference-rates --url 'https://ceadigital.io/mcp/sofr' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-ceadigital-nyfed-sofr-reference-rates:
    url: "https://ceadigital.io/mcp/sofr"
```

### Netclaw

```json
{
  "McpServers": {
    "io-ceadigital-nyfed-sofr-reference-rates": {
      "Transport": "http",
      "Url": "https://ceadigital.io/mcp/sofr"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-ceadigital-nyfed-sofr-reference-rates -t streamable-http -u 'https://ceadigital.io/mcp/sofr'
```

### Other

```json
{
  "mcpServers": {
    "io-ceadigital-nyfed-sofr-reference-rates": {
      "type": "http",
      "url": "https://ceadigital.io/mcp/sofr"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-20 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 75, +1)

- [security improvement] DNSSEC: fail → pass

### 2026-11-12 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-10 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-08 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (28)

### `gcp_catalog_search` (~73 tokens)

Sub-millisecond FTS5 search across 17,671 Google Cloud, Vertex AI, and A2A service records.

Input parameters:

- `limit` (integer): Max results to return (default 10)
- `query` (string, required): FTS5 search term (e.g. 'compute engine', 'vertex rag')

### `vault_knowledge_search` (~61 tokens)

FTS5 search across 36,628 video transcript chunks and 106,308 knowledge graph triples in vault.db.

Input parameters:

- `limit` (integer): Max chunk results (default 10)
- `query` (string, required): Search term for creator knowledge graph

### `sec_edgar_cik_lookup` (~76 tokens)

SEC EDGAR company submission facts, quarterly filings, and CIK lookup under Lowe v. SEC Publisher's Exclusion.

Input parameters:

- `cik` (string): 10-digit zero-padded SEC CIK identifier
- `ticker` (string): Company stock ticker symbol (e.g. AAPL, MSFT, COIN)

### `github_repo_pulse` (~56 tokens)

Extract repository activity pulse (stars, forks, open issues, license, last push) with ETag caching.

Input parameters:

- `owner` (string, required): GitHub repository owner or organization
- `repo` (string, required): GitHub repository name

### `security_cve_audit` (~75 tokens)

Audit package vulnerabilities and CVE advisories via OSV.dev database.

Input parameters:

- `ecosystem` (string): Ecosystem (PyPI, npm, Go, etc.)
- `package` (string, required): Package name (e.g. 'jinja2', 'requests')
- `version` (string): Specific version string (optional)

### `package_health_pulse` (~33 tokens)

Parallel health pulse inspection across NPM and PyPI ecosystems.

Input parameters:

- `package_name` (string, required): Target package name

### `fdic_bank_health` (~82 tokens)

Factual public supervisory bank health and branch metrics compiled from FDIC under 12 CFR Part 328.

Input parameters:

- `cert` (string): FDIC Certificate Number (e.g. 628)
- `limit` (integer): Max institutions to return (default 10)
- `name` (string): Bank name to search (e.g. Chase, Wells Fargo)

### `openalex_citation_graph` (~102 tokens)

Academic citation graph metadata and scholarly network metrics from OpenAlex (CC0).

Input parameters:

- `doi` (string): Digital Object Identifier (e.g. 10.1038/s41586-020-2649-2)
- `limit` (integer): Max citation entries (default 10)
- `query` (string): Scientific topic or title search
- `work_id` (string): OpenAlex Work ID (e.g. W2741809807)

### `usgs_seismic_hazard` (~123 tokens)

Seismic activity and earthquake risk profiles from USGS GeoJSON services.

Input parameters:

- `endtime` (string): End date (YYYY-MM-DD)
- `latitude` (number): Center latitude coordinate
- `limit` (integer): Max seismic events to return (default 20)
- `longitude` (number): Center longitude coordinate
- `maxradiuskm` (number): Radius in km from center coordinate
- `minmagnitude` (number): Minimum earthquake magnitude (default 2.5)
- `starttime` (string): Start date (YYYY-MM-DD)

### `dexscreener_token_audit` (~120 tokens)

Real-time DEX liquidity, price, pair volume, and market cap analytics via DexScreener.

Input parameters:

- `chain_id` (string): Chain identifier (e.g. base, ethereum, solana)
- `query` (string): Token symbol or name search (e.g. USDC, VIRTUAL)
- `token_address` (string): Smart contract token address (e.g. 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913)

### `npi_medical_registry` (~121 tokens)

CMS NPPES NPI Registry lookup for healthcare organizations and facilities (NPI-2 only, HIPAA safe harbor).

Input parameters:

- `city` (string): City name
- `limit` (integer): Max organizations to return (default 10)
- `number` (string): 10-digit National Provider Identifier (NPI)
- `organization_name` (string): Healthcare organization or facility name
- `postal_code` (string): Postal code
- `state` (string): 2-letter US state code (e.g. CA, NY, MN)

### `crtsh_cert_recon` (~50 tokens)

Query Sectigo Certificate Transparency logs (crt.sh) for issued SSL/TLS certificates and subdomains.

Input parameters:

- `domain` (string, required): Target domain (e.g. stripe.com, coinbase.com)

### `epss_exploit_score` (~65 tokens)

Query FIRST.org Exploit Prediction Scoring System (EPSS) for 30-day real-world exploit probability.

Input parameters:

- `cve` (string, required): CVE identifier (e.g. CVE-2024-3094, CVE-2021-44228)

### `gleif_lei_kyb` (~53 tokens)

Query Global Legal Entity Identifier Foundation (GLEIF) registry for corporate KYB and LEI records.

Input parameters:

- `name` (string, required): Legal entity name (e.g. Coinbase, Stripe, BlackRock)

### `cfpb_complaints` (~56 tokens)

Query US Consumer Financial Protection Bureau (CFPB) complaint database (17 U.S.C. § 105 public domain).

Input parameters:

- `company` (string, required): Company or bank name (e.g. Wells Fargo, Equifax)

### `usaspending_awards` (~55 tokens)

Query USASpending.gov Federal Awards and Contractor Intelligence (17 U.S.C. § 105 public domain).

Input parameters:

- `recipient` (string, required): Federal contractor or recipient name (e.g. Palantir, SpaceX)

### `depsdev_openssf_scorecard` (~117 tokens)

Query Google Open Source Insights (deps.dev) and Linux Foundation OpenSSF Security Scorecard (0-10) for any GitHub repository or package (#1 in MCP Registry).

Input parameters:

- `ecosystem` (string): Package ecosystem: pypi, npm, go, cargo, maven
- `github_repo` (string): GitHub owner/repo (e.g. 'psf/requests', 'fastapi/fastapi')
- `package` (string): Package name (e.g. 'requests', 'express')

### `nyfed_sofr_reference_rates` (~63 tokens)

Query Federal Reserve Bank of New York official Secured Overnight Financing Rate (SOFR) benchmark rates, percentiles, and daily repo volume (#1 in MCP Registry).

Input parameters:

- `limit` (integer): Number of recent daily SOFR observations (default 5)

### `cisa_kev_exploited_vulns` (~119 tokens)

Query US CISA Known Exploited Vulnerabilities (KEV) Catalog for active in-the-wild exploitation, mandatory federal patch due dates, and ransomware usage.

Input parameters:

- `cve` (string): CVE identifier (e.g. CVE-2024-3094, CVE-2021-44228)
- `limit` (integer): Max KEV records to return (default 10)
- `vendor` (string): Vendor or product keyword filter (e.g. Microsoft, Linux, Cisco)

### `corporate_kyb_and_risk_dossier` (~110 tokens)

5-Source Parallel Composite Dossier: Joins GLEIF LEI + SEC EDGAR + CFPB Complaints + USASpending Federal Awards + FDIC in <400ms with a 0-100 Counterparty Verification Score.

Input parameters:

- `company_name` (string, required): Company or institution name (e.g. Coinbase, Wells Fargo, Palantir)
- `ticker` (string): Optional stock ticker (e.g. COIN, WFC, PLTR)

### `cyber_supply_chain_security_dossier` (~188 tokens)

5-Source Parallel Security Dossier: Joins crt.sh SSL Certs + Google deps.dev OpenSSF Scorecard + FIRST.org EPSS + CISA KEV + OSV.dev CVEs in <400ms with a 0-100 Security Posture Score.

Input parameters:

- `cve` (string): CVE ID for EPSS + CISA KEV check (e.g. CVE-2024-3094)
- `domain` (string): Target domain for crt.sh subdomain/SSL recon (e.g. stripe.com)
- `ecosystem` (string): Ecosystem (PyPI, npm, Go)
- `github_repo` (string): GitHub owner/repo for OpenSSF Scorecard (e.g. psf/requests)
- `package` (string): Package name for OSV CVE audit (e.g. requests, jinja2)

### `agent_compliance_notary_attest` (~121 tokens)

Tamper-evident SHA-256 hash-chained Agent Decision & Compliance Notary for EU AI Act, NIST AI RMF, and SOC2 autonomous agent audit trails.

Input parameters:

- `action_type` (string): Action category (e.g. TRADE_EXECUTION, KYB_APPROVAL, CODE_AUDIT)
- `agent_id` (string): Autonomous agent identifier
- `payload_sha256` (string): Optional SHA-256 digest of input/output payload
- `summary` (string, required): Sanitized decision summary for immutable audit log

### `submit_feedback_or_rate_quote` (~178 tokens)

Free interactive MCP feedback, feature requests, and custom rate quote negotiation (alias: submit_mcp_feedback_or_request).

Input parameters:

- `agent_or_contact` (string): Agent client name or contact handle (optional)
- `category` (string): Feedback category: mcp_improvement, new_mcp_request, pricing_rate_quote, or compliance_privacy_note
- `desired_rate_usd` (string): Desired per-call or pool rate quote (e.g. '$0.005/call', 'swarm_pool')
- `mcp_target` (string): Target MCP server or endpoint being reviewed
- `message` (string, required): Detailed feedback, schema change request, or rate proposal
- `rating` (integer): Satisfaction score 1-5 (default 5)
- `source_surface` (string): Surface identifier (default 'mcp_tool')

### `agent_token_intel_and_honeypot` (~132 tokens)

High-velocity Agent Operational Primitive ($0.005 USDC on Base): Real-time DEX pool liquidity, 24h volume, buy/sell execution symmetry, Base bytecode check, and deterministic 0-100 Honeypot & Anti-Rug Safety Score.

Input parameters:

- `chain` (string): Target chain (base, ethereum, solana, arbitrum)
- `token_address` (string, required): Token contract address (e.g. 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913)

### `agent_clean_web_grounding` (~85 tokens)

High-velocity Agent Operational Primitive ($0.008 USDC on Base): Fast, token-optimized real-time web grounding & clean Markdown synthesis stripped of HTML bloat, ads, and scripts for LLM context windows.

Input parameters:

- `limit` (integer): Max grounded blocks (default 5)
- `query` (string, required): Search topic or technical query for clean Markdown grounding

### `agent_base_tx_simulate` (~129 tokens)

High-velocity Agent Operational Primitive ($0.005 USDC on Base): Pre-execution Base L2 (eip155:8453) calldata simulator & wallet drain guard via eth_call + eth_estimateGas + unlimited ERC-20 approve detection.

Input parameters:

- `data` (string): Hex calldata (e.g. 0x18160ddd)
- `from_address` (string): Sender wallet address for simulation
- `to_address` (string, required): Target contract or recipient address on Base
- `value_wei` (string): ETH value in hex wei (default 0x0)

### `provision_free_developer_key` (~106 tokens)

FREE Self-Serve API Key Generator: Instantly mints a 50-call free starter `cea_live_` Bearer token with copy-paste snippets for Claude Desktop, Cursor, Windsurf, ElizaOS, and Coinbase AgentKit.

Input parameters:

- `agent_name` (string): Agent or developer identifier
- `contact` (string): Optional handle or contact
- `framework` (string): Client framework (claude-desktop, cursor, elizaos, agentkit)

### `agent_url_to_clean_markdown` (~107 tokens)

High-velocity Agent Operational Primitive ($0.005 USDC on Base): Live URL-to-Clean-Markdown extractor competing with Firecrawl/Jina. Fetches any public URL via SSRF-safe HTTP + LegalTDMGuard and returns clean, prompt-injection-scrubbed Markdown.

Input parameters:

- `max_chars` (integer): Maximum Markdown characters to return (default 16000)
- `url` (string, required): Public HTTP/HTTPS URL to fetch and convert into clean Markdown

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-ceadigital-nyfed-sofr-reference-rates/mcp-sofr#diagnostics

## Score history

- 2026-11-21: 79
- 2026-11-20: 79
- 2026-11-19: 78
- 2026-11-18: 78
- 2026-11-17: 77
- 2026-11-16: 77
- 2026-11-15: 76
- 2026-11-14: 76
- 2026-11-13: 75
- 2026-11-12: 74
- 2026-11-11: 73
- 2026-11-10: 73
- 2026-11-09: 72
- 2026-11-08: 72
- 2026-11-07: 71
- 2026-11-06: 71
- 2026-11-05: 70

## Common questions

### What is the NY Fed SOFR, EFFR & OBFR Overnight Benchmark Reference Rates MCP server?

NY Fed SOFR, EFFR & OBFR Overnight Benchmark Reference Rates is an MCP server listed in the public MCP registry as io.ceadigital/nyfed-sofr-reference-rates. Official Federal Reserve Bank of New York SOFR, EFFR, and OBFR overnight reference rates. This page covers its hosted endpoint (https://ceadigital.io/mcp/sofr).

### Is the NY Fed SOFR, EFFR & OBFR Overnight Benchmark Reference Rates MCP server safe to use?

NY Fed SOFR, EFFR & OBFR Overnight Benchmark Reference Rates scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the NY Fed SOFR, EFFR & OBFR Overnight Benchmark Reference Rates MCP server expose?

NY Fed SOFR, EFFR & OBFR Overnight Benchmark Reference Rates exposes 28 tools: gcp_catalog_search, vault_knowledge_search, sec_edgar_cik_lookup, github_repo_pulse, security_cve_audit, and 23 more. Their descriptions and schemas cost roughly 2,656 tokens of context every time the server is loaded.

### Does the NY Fed SOFR, EFFR & OBFR Overnight Benchmark Reference Rates MCP server require authentication?

No. We connected to NY Fed SOFR, EFFR & OBFR Overnight Benchmark Reference Rates without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the NY Fed SOFR, EFFR & OBFR Overnight Benchmark Reference Rates MCP server still maintained?

NY Fed SOFR, EFFR & OBFR Overnight Benchmark Reference Rates is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the NY Fed SOFR, EFFR & OBFR Overnight Benchmark Reference Rates MCP server?

VerifyMCP ran 13 checks on NY Fed SOFR, EFFR & OBFR Overnight Benchmark Reference Rates, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://ceadigital.io/mcp/sofr
- Website: https://ceadigital.io/
- Changelog RSS feed: https://verifymcp.io/servers/io-ceadigital-nyfed-sofr-reference-rates/mcp-sofr.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-ceadigital-nyfed-sofr-reference-rates/mcp-sofr/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/io-ceadigital-nyfed-sofr-reference-rates/mcp-sofr.json
- HTML version of this page: https://verifymcp.io/servers/io-ceadigital-nyfed-sofr-reference-rates/mcp-sofr
