Skip to main content
Glama
omarnagy91
by omarnagy91

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
load_documentA

Load a contract and return its normalised text with a citation anchor on every paragraph, plus the detected language mix. Start here. Returns the format, page count where the format has pages, per paragraph text direction for correct rendering of mixed Arabic and English, any encoding repairs that were applied, and any warnings such as a PDF with a lossy or missing text layer. Paragraph anchors look like "P12" and are the same anchors every other tool reports.

segment_clausesA

Split the document into numbered clauses and headings, handling English and Arabic numbering conventions. English decimal (1, 1.1, 1.1.1), lettered and roman sub items, and the Arabic conventions المادة (٣), البند الأول, standalone ordinals أولاً and ثانياً, and Arabic decimal ٣-٢ written with a hyphen. Each clause gets a stable anchor such as "C14", its label exactly as the document writes it, an ASCII normalised label for comparison, its nesting depth, its parent clause, and the paragraph anchors it covers. Cite these anchors so the reader can find the exact clause.

extract_datesA

Extract every date, classify what it is for, and compute the deadlines that follow from it. Handles Gregorian and Hijri, Arabic-Indic and Persian digits, and month names in the Egyptian and Gulf, Levantine and Iraqi, and Hijri naming traditions. Each date reports its calendar, an ISO value, the role it plays (execution, commencement, term_end, renewal, notice, payment, delivery, signature) and the wording that justified that role. Hijri dates are converted with the tabular civil calendar and labelled as such, and where the contract states its own Gregorian equivalent any divergence is reported rather than resolved. Also returns notice periods found in the text and, where a fixed date anchors them, computed deadlines such as the date by which notice of non-renewal must be given.

extract_partiesA

Extract the parties, their defined terms and roles, their registration identifiers and addresses, and the signatories with their titles, each with an anchor. Reads both drafting traditions: the English numbered recital with a bracketed defined term, and the Arabic ordinal block with the ويشار إليه formula and the ويمثلها في التوقيع representative clause, which names the person who actually bound the company and is often the only place they are named.

find_clausesA

Find the clauses that deal with a legal concept and return their real text with anchors, so the model reviews the actual wording instead of a summary of it. Supported concepts: auto_renewal, unilateral_termination, penalty, governing_law, arbitration, confidentiality, non_compete, limitation_of_liability, notice, payment_terms, force_majeure, assignment, entire_agreement. Matching runs over an Arabic aware folded copy of the text, so a clause still matches whichever way it spells a term. Pass query instead of, or as well as, concept to search for free text. Results are ranked, and every result lists the terms that matched so the ranking can be audited.

document_summaryA

Build a structured skeleton of the contract for the model to reason over: parties and signatories, the term and whether it renews automatically, the obligations with the party bound by each, and the anchors of clauses that commonly need a closer look (auto renewal, unilateral termination, penalties, non compete, liability caps, arbitration). It returns structure and citations only. It contains no legal opinion, no risk rating and no recommendation, because those are the reviewing lawyer's to make.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.3/5.0

Scored across 6 tools

Disambiguation5/5

Each tool has a clearly distinct stage in the intake pipeline: load, segment, extract dates, extract parties, summarize, and search clauses. Although segment_clauses and find_clauses both involve clauses, one is structural segmentation and the other is semantic retrieval of actual wording, so there is no real ambiguity.

Naming Consistency4/5

Five tools follow a clean verb_noun snake_case pattern (load_document, segment_clauses, extract_dates, extract_parties, find_clauses). document_summary breaks the verb pattern and reads as a noun, which is a minor deviation but still readable and consistent in style.

Tool Count5/5

Six tools is a well-scoped set for a legal contract intake server. It covers ingestion, structural segmentation, date extraction, party extraction, summarization, and semantic clause retrieval without redundancy or unnecessary bloat.

Completeness5/5

The surface covers the full intake pipeline: load and normalize the document, segment clauses, extract dates and parties, build a structured summary, and retrieve the actual wording of relevant clauses. There are no obvious dead ends or missing operations that would prevent an agent from completing a contract intake workflow.

Maintenance

ActivityMaintained
ResponsivenessNo issues