claude-edgar-mcp
Provides tools for accessing SEC EDGAR filings, including resolving stock tickers to CIK numbers.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@claude-edgar-mcpWhat is Apple's SEC CIK?"
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.
claude-edgar-mcp
A Model Context Protocol server that gives Claude, GPT, or any MCP-compatible LLM direct access to SEC EDGAR — the US Securities and Exchange Commission filings database used by every equity analyst on Wall Street.
Tools
Tool | What it does |
`ticker_to_cik` | Resolves a US stock ticker to its SEC Central Index Key (CIK) |
More tools coming — see roadmap.
Related MCP server: Finance MCP Server
Example
Ask Claude:
What is Meta's SEC CIK?
Claude calls `ticker_to_cik("META")` and returns:
```json { "ticker": "META", "cik": "0001326801", "company_name": "Meta Platforms, Inc." } ```
Install
```bash git clone https://github.com/mmouradbahri/claude-edgar-mcp.git cd claude-edgar-mcp uv sync ```
Wire into any MCP-compatible client
Claude Desktop: edit `~/Library/Application Support/Claude/claude_desktop_config.json`:
```json { "mcpServers": { "claude-edgar-mcp": { "command": "/Users/YOU/.local/bin/uv", "args": ["--directory", "/PATH/TO/claude-edgar-mcp", "run", "main.py"] } } } ```
OpenAI Codex CLI: edit `~/.codex/config.toml`:
```toml [mcp_servers.claude-edgar-mcp] command = "/Users/YOU/.local/bin/uv" args = ["--directory", "/PATH/TO/claude-edgar-mcp", "run", "main.py"] ```
Restart your client. Works with Claude Desktop, Claude Code, OpenAI Codex, Cursor, VS Code + Copilot, and Gemini CLI.
Roadmap
v0.2 — `get_recent_filings(ticker, filing_type, limit)` — return list of a company's recent 10-K/10-Q/8-K filings
v0.3 — `get_10k_url(ticker)` — direct URL to a company's latest 10-K
v0.4 — `get_10k_section(accession, section)` — extract Business, Risk Factors, MD&A from a specific filing
v0.5 — `get_financials(ticker, years)` — pull revenue, net income, FCF from XBRL
Built by Mourad Bahri — part of a broader AI × financial-services project.
Available Tools
1 toolticker_to_cikA
Resolve a US stock ticker to its SEC Central Index Key (CIK).
Use this whenever a user gives you a ticker (like 'AAPL' or 'META') and
you need to look up SEC filings for that company. Every other EDGAR tool
starts with a CIK.
Args:
ticker: The stock ticker (case-insensitive), e.g. 'AAPL', 'META', 'WING'.
Returns:
Dict with `ticker`, `cik` (10-digit zero-padded string), and `company_name`.
| Name | Required | Description | Default |
|---|---|---|---|
| ticker | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description covers the behavior: it is a simple lookup, case-insensitive, returning a dict with ticker, cik, and company_name. It does not mention any side effects or authorization needs, which is acceptable for a read-only mapping.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is structured with a clear statement, usage guidance, then Args/Returns sections. It is concise (5 sentences) and front-loaded with the main purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given only 1 parameter and no output schema, the description fully explains the input and output format, including the zero-padded cik. It is complete for this simple tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but the description explains the 'ticker' parameter with examples and case-insensitivity, adding meaning beyond the schema's type and title.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it resolves a US stock ticker to its SEC CIK using a specific verb-resource structure. It provides examples like 'AAPL' and 'META', making the purpose immediately clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Use this whenever a user gives you a ticker... and you need to look up SEC filings' and notes that other EDGAR tools start with a CIK. It provides clear context for when to use, though it does not list specific siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
v0.1.0- First observed
ticker_to_cik
TDQS
With only one tool, there is no possible confusion with other tools. The tool's purpose is clearly defined.
The name 'ticker_to_cik' uses underscores and describes input and output, but does not follow a verb_noun pattern. However, it is descriptive and consistent with a single-tool set.
One tool is very minimal for a server named 'claude-edgar-mcp', which implies broader EDGAR functionality. The tool only resolves tickers to CIKs, missing essential operations like filing retrieval or search.
The server provides only a ticker-to-CIK conversion, which is a prerequisite for EDGAR access but not useful alone. There are no tools to actually retrieve or search SEC filings, leaving a critical gap.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
SEC EDGAR filings for AI agents: company lookup, filings, financials, insider trades. No keys.
SEC EDGAR filings for AI agents: company lookup, filings, financials, insider trades. No keys.
EDGAR MCP — SEC EDGAR public APIs (free, no auth)
Provide AI assistants with real-time access to official SEC EDGAR filings and financial data. Enab…
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAdds tools for SEC EDGAR research: lookup company CIK, search filings, and fetch filing text.86MIT
- FlicenseNot gradedqualityBmaintenanceEnables fetching real-time financial market data, including price, key metrics, and news headlines, for stock tickers using the yfinance API.75-
- AlicenseNot gradedqualityCmaintenanceEnables to search and retrieve SEC EDGAR filings, insider transactions, major shareholders, and executive compensation data through natural language.25MIT
- AlicenseAqualityBmaintenanceEnables searching SEC EDGAR filings by full-text search and listing company filings, with accurate company name resolution to CIKs in code, avoiding hallucinated identifiers.230MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/mmouradbahri/claude-edgar-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server