Skip to main content
Glama
PrinceGabriel-lgtm

freshcontext-mcp

by PrinceGabriel-lgtm
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

extract_company_landscape

Read-only

Extracts comprehensive company intelligence from five sources: SEC filings, federal contracts, global news, product changelogs, and market quotes. Provides a unified timestamped report.

Instructions

Composite company intelligence tool. The most complete single-call company analysis available. Simultaneously queries 5 unique sources: (1) SEC EDGAR for 8-K material event filings — what the company legally just disclosed, (2) USASpending.gov for federal contract footprint — who is giving them government money, (3) GDELT for global news intelligence — what the world is saying about them right now, (4) their product changelog — are they actually shipping, (5) Stooq quote data — what the market is pricing in. Returns a unified 5-source timestamped report. Unique: this combination is not available in any other MCP server.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tickerNoStock ticker for finance data e.g. 'PLTR'. Leave blank for private companies.
companyYesCompany name e.g. 'Palantir', 'Anthropic', 'OpenAI'
github_urlNoOptional GitHub repo or org URL e.g. 'https://github.com/palantir'. Improves changelog accuracy.
max_lengthNo
min_freshness_scoreNoFilter sections below this freshness_score (0–100). E.g. 70 = only recently retrieved data.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.1
    • addedInput schema / properties / min_freshness_score
      Added value: +{
+  "description": "Filter sections below this freshness_score (0–100). E.g. 70 = only recently retrieved data.",
+  "type": "number"
+}
  2. First observedv0.3.12

TDQS

A3.9/5.0
Behavior4/5

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

The description transparently lists the 5 data sources and states it returns a unified 5-source timestamped report. The readOnlyHint annotation is consistent, and no side effects are implied. It goes beyond the annotation by detailing the multi-source behavior.

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 somewhat long and includes marketing phrases ('most complete', 'not available in any other MCP server'), but the essential structure is clear and the information is well-organized. It does not waste space on irrelevant details.

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

Completeness4/5

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

Given the complexity of querying 5 sources, the description sufficiently explains the composite nature and the output (unified 5-source timestamped report). Parameter details like max_length and min_freshness_score are left to the schema, which is acceptable. No output schema exists, but the description sets expectations for the return type.

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

Parameters3/5

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

Schema description coverage is 80% (4 of 5 parameters documented). The tool description itself adds no additional parameter meaning beyond what the schema already provides, so baseline 3 is appropriate.

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 states what the tool does: a composite company intelligence tool that queries 5 unique sources and returns a unified report. It distinguishes itself from siblings by emphasizing the completeness and uniqueness of the combination.

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

Usage Guidelines3/5

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

The description implies use for comprehensive company analysis ('most complete single-call') and notes the combination is unique, but does not explicitly state when to choose this over alternatives like extract_finance or extract_landscape. Some guidance is given via the ticker parameter, but no direct when-to-use/when-not-to-use contrast.

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

Deploy Server

Other Tools