What can you do with this server?

This server lets you browse and retrieve Singapore legislation from the Attorney-General's Chambers' official portal (sso.agc.gov.sg), with verifiable citations on every response. Browse current Acts (sg_list_acts): Paginate through the current list of Singapore Acts (up to 100 results per page). Returns each Act's title, act code, a durable SSO URL (eli_uri), and a human-readable citation. Note: keyword/title search is not available, as SSO's robots.txt disallows /search. Fetch a specific provision (sg_get_provision): Retrieve the text of a single numbered section of any Act by providing its act_code (e.g., CoA1967) and section number. Returns the section text, caption, and full citation metadata. Fetch the full text of an Act (sg_get_full_text): Retrieve the complete text of an Act by act_code. Very large Acts are truncated at ~300,000 characters, with a truncated flag and byte_size indicator in the response. Every response includes: * eli_uri — a durable SSO Act URL * human_readable_citation — the Act title as rendered by SSO * source_url — for independent verification * dataset_note — context about the data source and citation scheme

How do I use sg-eli-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@sg-eli-mcp get section 25 of the Companies Act 1967" 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.

sg-eli-mcp

by matematicsolutions

Overview Schema Related Servers Score Discussions

Python

Remote

sg-eli-mcp

An MCP server for Singapore Statutes Online (SSO, sso.agc.gov.sg), the Attorney-General's Chambers' official portal for Singapore legislation. It browses, fetches, and cites Acts, with a verifiable citation on every response.

Part of the MateMatic eu-legal-mcp production line, extended into Asia alongside jp-eli-mcp. Same citation contract (a stable identifier + a human-readable citation + a source URL), adapted for a jurisdiction with no ELI and no public search API.

Scope. SSO's robots.txt disallows /search; discovery here is by browsing the current Acts listing (sg_list_acts, paginated), not by title or keyword query. Fetch a specific section (sg_get_provision) or the full text (sg_get_full_text, truncated for very large Acts). Every response carries a dataset_note.
Licence. SSO legislation is official public information published by the Singapore government. This connector relays it with attribution and a source_url, respects robots.txt (no /search calls), and does not cache more aggressively than a normal browser visit would.

The tools

Tool	What it does
`sg_list_acts`	Browse the current Acts, paginated (no keyword search - see Scope above).
`sg_get_provision`	The text of one numbered section of an Act, by `act_code` and section number.
`sg_get_full_text`	The full text of an Act (truncated at ~300,000 characters).
`sg_coverage`	Declare what this connector covers, when each family was captured, and - explicitly - what it does NOT cover. Every gap carries a fallback.

Every response carries the contract: eli_uri (Singapore has no ELI - this is the durable SSO act URL, e.g. https://sso.agc.gov.sg/Act/CoA1967, see eli_note), human_readable_citation (the Act title as SSO itself renders it, e.g. Companies Act 1967), and source_url.

Related MCP server: ie-eli-mcp

Install

Not yet on PyPI - install from source until the first release ships:

git clone https://github.com/matematicsolutions/sg-eli-mcp
cd sg-eli-mcp
pip install -e .

Once released, this will be uvx sg-eli-mcp.

Configuration via env:

SG_ELI_BASE_URL - default https://sso.agc.gov.sg
SG_ELI_CACHE_DIR - default ~/.matematic/cache/sg-eli
SG_ELI_AUDIT_DIR - default ~/.matematic/audit

No API key. SSO is keyless.

Configure (Claude Code / any MCP client)

{
  "mcpServers": {
    "sg-eli-mcp": { "command": "sg-eli-mcp" }
  }
}

Windows 11 with Smart App Control

Smart App Control blocks unsigned executables, which covers uvx.exe, pip.exe and the sg-eli-mcp.exe launcher that pip writes at install time. The python.exe and py.exe from the python.org installer are signed by the Python Software Foundation, so running the module through the interpreter works:

python -m pip install sg-eli-mcp
python -m sg_eli_mcp

pip.exe is blocked for the same reason, so install with python -m pip, not pip install. If python is not on PATH, use the Windows launcher: py -3 -m sg_eli_mcp.

{ "mcpServers": { "sg-eli-mcp": { "command": "python", "args": ["-m", "sg_eli_mcp"] } } }

Do not turn Smart App Control off to work around this - it cannot be re-enabled without reinstalling Windows.

Governance

Public data only - read-only against SSO; no client data leaves the machine.
Robots-compliant - never calls /search (disallowed by SSO's robots.txt); discovery uses only the allowed /Browse listing.
Audit log - every tool call appends one JSON line to ~/.matematic/audit/sg-eli-mcp.jsonl.
Vendor-neutral - talks only to sso.agc.gov.sg; no LLM provider, no telemetry.
Verifiable citations - every response is independently checkable via source_url.

See CONSTITUTION.md and DISCOVERY.md.

Tests

pip install -e ".[dev]"
pytest tests/test_instructions_drift.py -v   # offline
pytest tests/test_smoke.py -v                # hits live SSO

Licence

Apache-2.0. © Matematic Solutions / Wieslaw Mazur.

Available Tools

4 tools

sg_coverageA

Read-onlyIdempotent

Declare what this connector covers, how it is sourced, and what it does NOT cover.

Call this before telling a user that the law "does not contain" something, and whenever a search comes back empty: the absence may be a gap in this connector rather than in the law. Every gap carries a fallback saying where to look instead.

Returns: Coverage with families, an as-of note, and a non-empty list of known gaps.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`status`	No
`families`	No
`as_of_note`	Yes	States what the dates mean, and what they do not promise.
`known_gaps`	No	Never empty. An empty list would mean 'not checked', not 'no gaps'.

TDQS

A4.9/5.0

Behavior5/5

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

The description goes beyond the annotations by explaining the open-world behavior: an empty result may indicate a coverage gap, not a true absence in the law. It also discloses that every gap carries a fallback direction, and the return includes families, an as-of note, and a non-empty gap list.

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

Conciseness5/5

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

The description is well-structured: a clear one-line purpose, explicit usage guidance, and a concise return summary. Every sentence earns its place, and the key caveat about gaps is front-loaded.

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?

For a parameterless tool with rich annotations and an output schema, the description is complete. It covers what the tool returns, when to call it, and why the open-world caveat matters. Nothing needed for correct invocation is missing.

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

Parameters4/5

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

The tool has zero parameters, and the schema coverage is 100%, so there are no parameter semantics to clarify. The description adds useful return-format context instead, which is appropriate for a no-parameter tool.

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 the tool's function: declare what the connector covers, how it is sourced, and what it does NOT cover. It differentiates itself from siblings like sg_list_acts and sg_get_full_text by being about coverage rather than content retrieval.

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

Usage Guidelines5/5

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

The description gives explicit when-to-call guidance: before telling a user the law 'does not contain' something, and whenever a search returns empty, because absence may be a connector gap rather than a legal gap. This is highly actionable and leaves no ambiguity about when the tool is needed.

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

sg_get_full_textA

Read-onlyIdempotent

Fetch the full text of an act. Large acts are truncated.

ParametersJSON Schema

Name	Required	Description	Default
`act_code`	Yes	SSO's short act code, e.g. ``"CoA1967"`` (Companies Act 1967).

Output Schema

ParametersJSON Schema

Name	Required	Description
`title`	No
`content`	No
`eli_uri`	No
`act_code`	Yes
`eli_note`	No
`byte_size`	No
`truncated`	No
`source_url`	No
`dataset_note`	No
`human_readable_citation`	No

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already indicate read-only, non-destructive, idempotent behavior. The description adds an important behavioral warning: 'Large acts are truncated.' This goes beyond annotations and is critical for agent expectations.

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

Conciseness5/5

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

The description is extremely concise—two short sentences—with no wasted words. It front-loads the core action and adds a critical caveat. Perfect size for its simplicity.

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 tool's low complexity (1 required param, output schema exists), the description covers all necessary context: what it fetches, the truncation behavior, and the parameter. No gaps remain.

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 coverage is 100% with a clear description for act_code. The tool description does not add further parameter meaning beyond 'act code.' Baseline 3 is appropriate since the schema already handles parameter documentation.

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 the verb 'Fetch' and the resource 'full text of an act'. It also distinguishes from siblings: sg_get_provision retrieves a specific provision, and sg_list_acts lists acts, while this tool gets the entire act text.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention situations where sg_get_provision might be more appropriate for shorter excerpts, nor any prerequisites or context.

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

sg_get_provisionA

Read-onlyIdempotent

Fetch the text of one numbered section of an act.

ParametersJSON Schema

Name	Required	Description	Default
`act_code`	Yes	SSO's short act code, e.g. ``"CoA1967"`` (Companies Act 1967).
`provision_num`	Yes	the plain section number, e.g. ``"1"``.

Output Schema

ParametersJSON Schema

Name	Required	Description
`text`	No
`caption`	No
`eli_uri`	No
`act_code`	Yes
`eli_note`	No
`source_url`	No
`dataset_note`	No
`provision_num`	Yes
`human_readable_citation`	No

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint true and destructiveHint false, so the safety profile is clear. The description adds minimal behavioral context beyond fetching text, which is adequate given the annotations.

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

Conciseness5/5

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

The description is a single, front-loaded sentence that efficiently conveys the tool's purpose with no redundant information.

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?

The tool is simple with full schema coverage, good annotations, and an output schema present. The description, combined with structured data, provides complete context for selecting and invoking the tool.

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 100%, with clear descriptions for both parameters (act_code and provision_num). The tool description does not add further meaning, so baseline score of 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 specifies the verb 'Fetch' and resource 'text of one numbered section of an act', clearly distinguishing it from siblings like sg_get_full_text (full act text) and sg_list_acts (list acts).

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 does not explicitly state when to use this tool versus alternatives, but the sibling names imply the use case for single sections. No exclusions or context about prerequisites are provided.

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

sg_list_actsA

Read-onlyIdempotent

Browse Singapore's current Acts (paginated - SSO has no keyword search API).

ParametersJSON Schema

Name	Required	Description	Default
`page_size`	No	results per page, 1-100 (default 20).
`page_index`	No	1-based page number (default 1).

Output Schema

ParametersJSON Schema

Name	Required	Description
`items`	No
`page_size`	Yes
`page_index`	Yes
`dataset_note`	No

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already indicate read-only, idempotent, and open-world behavior. The description adds value by explaining pagination and the limitation of no keyword search API, which goes beyond the annotations. No contradiction found.

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 a single concise sentence that immediately communicates the purpose and key constraint. It is front-loaded and contains no redundant information, though it could be slightly more structured with minimal expansion.

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 presence of a full output schema, complete parameter descriptions, and informative annotations, the description adequately covers the tool's behavior and context. The limitation about keyword search is noted, making it sufficiently complete for a list tool.

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?

The input schema provides 100% coverage with clear descriptions for both parameters. The description mentions pagination but does not add significant new meaning beyond what the schema already states, so it meets the baseline without exceeding.

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 the tool browses Singapore's current Acts, using a specific verb and resource. It also mentions pagination and the limitation of no keyword search API, which distinguishes it from siblings like sg_get_full_text and sg_get_provision.

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 clear context by noting pagination and the absence of a keyword search API, implicitly advising when to use this tool (for browsing) and avoiding search use cases. However, it lacks explicit exclusions or direct sibling comparisons.

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 updatev0.3.3Aug 28, 2026
- Addedsg_coverage
3 tool updatesv0.1.0Jul 6, 2026
- First observedsg_get_full_text
- First observedsg_get_provision
- First observedsg_list_acts

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.2/5.0

Disambiguation5/5

Each tool targets a distinct action: listing acts, retrieving a single provision, retrieving full act text, and exposing connector coverage. There is no meaningful overlap that would cause an agent to select the wrong tool.

Naming Consistency4/5

Three tools follow a consistent sg_<verb>_<noun> pattern: sg_list_acts, sg_get_provision, and sg_get_full_text. The outlier is sg_coverage, which uses a bare noun instead of a verb_noun form, but the naming remains predictable overall.

Tool Count5/5

Four tools is a well-scoped size for a focused read-only legal retrieval connector. Each tool covers a distinct core need, and there are no redundant or unnecessary additions.

Completeness4/5

The set covers listing acts, fetching full text, and fetching individual provisions, with an explicit coverage tool that documents known gaps and fallbacks. It lacks a section index and paginated full-text continuation for large acts, but those gaps are surfaced rather than hidden.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Legal Mcp
io.github.varvararatta
MCP server for Legal
Legal & Compliance Documentation Access
2
hithereiamaliff-mcp-datagovmy BOAuth
ai.smithery
This MCP server provides seamless access to Malaysia's government open data, including datasets, w…
Government Data Open Data
23
mcpOAuth
com.bullpenstrategygroup.rotunda
An MCP server that provides congressional transcripts
Government Data Search Open Data
2
thoughtsOAuth
ai.thoughtbox.api
An MCP server that provides read access to your cloud storage providers, bank accounts and more.
Cloud Storage Finance
2

Related MCP Servers

GCC Docs MCP Server
Government Data Documentation Access
Fredwong76
F
license
Not graded
quality
C
maintenance
An MCP server that indexes Singapore Government GCC documentation and exposes search tools for AI assistants.
Updated 2 months ago (2026-06-22 10:39 UTC)
-
ie-eli-mcp
Government Data Legal & Compliance
matematicsolutions
A
license
A
quality
A
maintenance
An MCP server that provides access to the Irish Statute Book, enabling retrieval of metadata and full enacted text for Irish acts and statutory instruments by year, number, and type, with verifiable ELI identifiers and citations.
Updated 13 days ago (2026-08-24 13:56 UTC)
3
Apache 2.0
au-eli-mcp
Government Data Search
matematicsolutions
A
license
A
quality
A
maintenance
MCP server for Australia's Federal Register of Legislation. Enables searching and fetching Commonwealth Acts with verifiable citations.
Updated 13 days ago (2026-08-24 13:54 UTC)
3
Apache 2.0
my-eli-mcp
Legal & Compliance Government Data
matematicsolutions
A
license
A
quality
A
maintenance
MCP server for the Laws of Malaysia Online portal, fetching and citing Malaysian principal Acts with verifiable citations.
Updated 13 days ago (2026-08-24 13:57 UTC)
3
Apache 2.0

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/matematicsolutions/sg-eli-mcp'

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