Skip to main content
Glama
henrysouchien

fmp-mcp

by henrysouchien
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

get_earnings_transcript

Retrieve earnings call transcripts for any company, split into prepared remarks and Q&A with speaker and role filters.

Instructions

Parse and navigate an earnings call transcript.

Splits the raw transcript into structured sections: prepared remarks and Q&A with per-speaker segments and grouped Q&A exchanges.

IMPORTANT — default mode is summary (metadata only). This protects your context window. Full text is returned only when you explicitly request format="full".

Recommended workflow:

  1. Call with default format="summary" to see the speaker list, word counts, and exchange count (costs ~1 KB of context)

  2. Identify the section or speaker you need

  3. Call again with format="full" and specific filters (section, filter_role, filter_speaker) to read only that content

  4. Each text field is capped at max_words (default 3000). Set max_words=None to remove the cap (use with caution). Note: If format="full" is used WITHOUT any filters (no section, filter_role, or filter_speaker), a bounded preview is returned instead (first 3 segments per section, 500 words each, 2 exchanges). Add at least one filter to get full content with max_words control.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yearYesFiscal year of the earnings call (e.g., 2024).
formatNoOutput format: - "summary": Metadata only — speaker list, word counts, exchange count. No text content. This is the DEFAULT. Use this first to scout the transcript before reading full text. - "full": Text content for all matching segments, truncated to max_words per field.summary
outputNoOutput mode: - "inline": Return content in MCP response (default). - "file": Write full untruncated markdown to disk and return metadata + absolute file_path.inline
symbolYesStock symbol (e.g., "AAPL", "MSFT", "NVDA").
quarterYesQuarter 1-4.
sectionNoWhich section to return: - "all": Both prepared remarks and Q&A (default) - "prepared_remarks": Management presentations only - "qa": Q&A session onlyall
max_wordsNoMaximum words per text field when format="full". Default 3000. Set to None for unlimited (use with caution — CEO prepared remarks can exceed 5K words). Ignored when format="summary" or output="file".
filter_roleNoFilter to segments by role: - "CEO", "CFO", "COO", "CTO": C-suite executives - "Analyst": Sell-side analysts asking questions - "IR": Investor Relations host - "Operator": Call operator
filter_speakerNoFilter to segments by this speaker (substring match, e.g., "Cook" matches "Tim Cook"). Case-insensitive.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Tool Definition Quality

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries full responsibility. It thoroughly discloses key behaviors: default format is summary to protect context, full mode returns bounded preview when unfiltered, max_words cap, and output mode differences (inline vs file). This covers potential pitfalls and resource usage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with bullet points and clear sections, but it is somewhat lengthy. The recommended workflow is stated in two places (paragraph form and list), introducing minor redundancy. Still, it is easy to scan and logically ordered.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the 9 parameters and the existence of an output schema, the description covers all critical aspects: parameter explanations, behavioral nuances, workflow guidance, and trade-offs. It prepares the agent for complex usage scenarios like avoiding massive context consumption.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description adds significant value beyond parameter names and types. It explains default values, interactions (e.g., max_words ignored in summary or file mode), filtering behavior (substring match, case-insensitive), and the bounded preview logic. This rich contextual information is essential for correct usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as parsing and navigating earnings call transcripts, explaining the structured output (prepared remarks and Q&A). It distinguishes itself from sibling tools, which are other financial data retrieval tools, by focusing specifically on earnings transcript content and navigation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a step-by-step recommended workflow: start with summary to scout, then use full with filters. It warns about context window size, explains the bounded preview behavior when no filters are provided, and describes when to use inline vs file output. However, it does not explicitly state when not to use this tool or compare to alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

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/henrysouchien/fmp-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server