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., "@Knesset MCP Server אילו סיעות פעילות כיום בכנסת ה-25?"
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.
A Model Context Protocol (MCP) server for accessing the Israeli Knesset's parliamentary information API. Exposes a focused set of tools so AI assistants like Claude can query bills, committees, and members from the Knesset OData service.
Node.js >= 20.10.0 (older versions fail with SELF_SIGNED_CERT_IN_CHAIN against knesset.gov.il)
Related MCP server: Data.gov.il MCP Server
git clone https://github.com/yourusername/knesset-mcp-server.git
cd knesset-mcp-server
npm install
npm run buildnpm start # run the built server
npm run dev # run TypeScript directly via ts-nodeInstall Claude Desktop.
Edit your Claude Desktop configuration at ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"knesset": {
"command": "npx",
"args": ["-y", "knesset-mcp"]
}
}
}Restart Claude Desktop — the Knesset tools will be available.
The npx -y flag auto-installs the package on first run and caches it. Requires Node.js >= 20.10.0.
get-bill-info — Detailed info for a bill by BillID, including initiators.
search-bills-by-name — Keyword search over bill names (up to 20 most recent matches). Optional knessetNum filter.
list-bills-by-status — Bills filtered by a raw StatusID from KNS_Status, ordered by LastUpdatedDate desc.
list-recent-bills-by-stage — Bills at a named legislative stage:
first-reading-approved, first-reading-plenum, second-third-approved, second-third-plenum, third-reading-plenum, passed.
Note: the Knesset combines 2nd and 3rd readings into one vote, so second-third-approved is the closest proxy to "passed second reading"; passed means the bill became law.
list-bills-by-type — Bills by origin: private, government, or committee. Optional knessetNum.
get-committee-info — Committee details by CommitteeID.
list-committees — Committees for a given Knesset number, with optional onlyCurrent filter.
list-factions — Lists parties (factions) in a given Knesset. Use this first to find the FactionID of the party you care about. Optional onlyCurrent filter to exclude factions that have disbanded or merged.
list-knesset-members — Lists Knesset members (MKs) with their party affiliation. Optional factionId filter returns only members of a specific party (pair with list-factions to discover IDs). Optional onlyCurrent filter limits results to active memberships.
How to get a party's MK roster:
Call list-factions with the Knesset number → find the FactionID of the party.
Call list-knesset-members with that knessetNum and factionId → get the member list.
Note: an MK who switched parties mid-term appears once per stint. Pass onlyCurrent: true to see only the active membership.
Sample prompts in Hebrew you can try once the server is wired up. Each one exercises a specific tool or combination of tools.
list-factions
"אילו סיעות פעילות כיום בכנסת ה-25?"
"תראה לי את כל הסיעות שהיו בכנסת ה-24, כולל כאלה שהתפצלו או התאחדו."
list-knesset-members
"מי חברי סיעת הליכוד בכנסת הנוכחית?"
"תן לי את רשימת כל חברי הכנסת המכהנים כרגע בכנסת ה-25."
list-committees
"אילו ועדות פעילות היום בכנסת?"
"מה הן כל הוועדות שפעלו בכנסת ה-24?"
get-committee-info
"תן לי פרטים על ועדת הכספים."
"מה המידע על הוועדה עם המזהה 2010?"
search-bills-by-name
"חפש הצעות חוק שמכילות את המילה 'פנסיה'."
"מצא הצעות חוק על 'דיור ציבורי' בכנסת ה-25."
list-bills-by-type
"תראה לי את הצעות החוק הממשלתיות האחרונות בכנסת ה-25."
"מה הן 20 הצעות החוק הפרטיות העדכניות ביותר?"
list-bills-by-status
"אילו הצעות חוק עברו בקריאה שלישית לאחרונה (סטטוס 118)?"
"תן לי את הצעות החוק שאושרו בוועדה לקריאה שנייה ושלישית בכנסת ה-25."
list-recent-bills-by-stage
"אילו חוקים עברו ונכנסו לספר החוקים לאחרונה?"
"תן לי את ההצעות שאושרו בקריאה ראשונה בכנסת הנוכחית."
get-bill-info
"תן לי את כל הפרטים והיוזמים של הצעת החוק עם המזהה 2145694."
"מי יזם את הצעת החוק הזו ומה הסטטוס הנוכחי שלה? (BillID: ...)"
Two tools
"תראה לי את כל הסיעות החרדיות בכנסת ה-25, ואז פרט את חברי הכנסת של 'יהדות התורה'." → list-factions + list-knesset-members
"חפש הצעות חוק על 'אלימות במשפחה' בכנסת הנוכחית, ואז תן לי את הפרטים המלאים והיוזמים של הכי רלוונטית." → search-bills-by-name + get-bill-info
"תראה לי את כל הוועדות הפעילות בכנסת, ואז תן לי את המידע המפורט על ועדת החוקה." → list-committees + get-committee-info
"אילו חוקים עברו בקריאה שלישית לאחרונה? בחר את 3 החשובים ביותר ותן לי פרטים על כל אחד." → list-recent-bills-by-stage + get-bill-info
Three tools
"מצא את הסיעה 'יש עתיד' בכנסת ה-25, ראה מי חבריה, ואז חפש הצעות חוק שמזכירות אחד מהם בשם — בחר את מרב מיכאלי לדוגמה." → list-factions + list-knesset-members + search-bills-by-name
"תראה לי 10 הצעות חוק ממשלתיות אחרונות ו-10 הצעות פרטיות אחרונות, ואז פרט את ההצעה הפרטית שהכי מתקדמת בתהליך החקיקה." → list-bills-by-type (×2) + get-bill-info
"חפש הצעות חוק על 'תחבורה ציבורית', סנן את אלו שאושרו לקריאה ראשונה (סטטוס 109), ותן לי פרטים על הפעילה ביותר." → search-bills-by-name + list-bills-by-status + get-bill-info
Four or more tools
"צור לי פרופיל שלם של סיעת 'העבודה' בכנסת ה-25: רשימת החברים, באילו ועדות הם פעילים, ודוגמה להצעת חוק שהם יזמו. התחל ממציאת מזהה הסיעה." → list-factions + list-knesset-members + list-committees + search-bills-by-name + get-bill-info
"הכן לי סיכום חקיקה: 5 חוקים שעברו לאחרונה, 5 הצעות שאושרו לקריאה שנייה-שלישית, ו-5 הצעות שאושרו לקריאה ראשונה — עבור הכנסת הנוכחית. עבור החוק החשוב ביותר שעבר, תן לי את הפרטים המלאים." → list-recent-bills-by-stage (×3) + get-bill-info
"אני מתעניין בחקיקת סביבה. חפש הצעות חוק על 'אקלים' ו'זיהום', תן לי פרטים על כל אחת כולל היוזמים, ובדוק לאיזו סיעה משתייך כל יוזם — האם זה חוצה קואליציה/אופוזיציה?" → search-bills-by-name + get-bill-info + list-factions + list-knesset-members
Backed by the Knesset OData service at:
https://knesset.gov.il/Odata/ParliamentInfo.svcOrdering uses LastUpdatedDate because the OData API does not expose per-stage transition dates on KNS_Bill.
For ad-hoc testing of the server you can use the MCP Inspector:
npx @modelcontextprotocol/inspector node build/knesset-mcp-server.jsA minimal smoke test is included:
node test-mcp.mjsMIT
Get detailed information about a specific bill by its BillID, including initiators.
| Name | Required | Description | Default |
|---|---|---|---|
| billId | Yes | KNS_Bill BillID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only mentions that it returns detailed information and includes initiators, but fails to discuss authentication, rate limits, error handling, or data sensitivity.
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?
A single concise sentence that front-loads the verb and resource. Every word is necessary and contributes to clarity.
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?
For a simple single-parameter read tool, the description is adequate but lacks details on return format, error conditions, or pagination. It is minimally complete.
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 100%, so baseline is 3. The description references the billId parameter implicitly but does not add any additional meaning or constraints beyond what the schema already provides.
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 the action 'Get', the resource 'detailed information about a specific bill', the identifier 'by its BillID', and includes the content 'including initiators'. It effectively distinguishes from sibling list/search tools.
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 implies use when a specific BillID is known but does not explicitly state when to use this tool versus alternatives like 'search-bills-by-name' or list tools. No exclusions or alternative guidance are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get information about a specific committee by its CommitteeID.
| Name | Required | Description | Default |
|---|---|---|---|
| committeeId | Yes | KNS_Committee CommitteeID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses no behavioral traits beyond simply stating it retrieves information. There is no mention of read-only nature, rate limits, prerequisites, or what the response contains.
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 very short and front-loaded, which is concise, but it sacrifices necessary detail for brevity. It could be expanded slightly without losing conciseness.
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?
There is no output schema and no annotations. The description does not explain what information is returned or any other details. For a simple retrieval tool, more completeness is expected to guide the agent on expected output.
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?
With 100% schema description coverage, the schema already documents the parameter's meaning. The description adds no additional semantic value beyond repeating the parameter's role.
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 the verb 'Get information' and the resource 'a specific committee', and identifies the required CommitteeID. It effectively distinguishes from sibling tools like 'list-committees' which lists all committees.
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?
No guidance is provided on when to use this tool vs alternatives. It implicitly suggests using it when you have a CommitteeID, but there is no explicit exclusion or context for when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List recent bills filtered by StatusID (from KNS_Status), ordered by LastUpdatedDate descending. Ordering uses LastUpdatedDate since the OData API does not expose per-stage transition dates on KNS_Bill.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max bills to return (default 10) | |
| statusId | Yes | KNS_Status StatusID. Common: 118=passed third reading, 178/179=approved in committee for 2nd-3rd reading, 109/167=approved for first reading | |
| knessetNum | No | Optional Knesset number to filter by |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must cover behavior. It mentions ordering and an API limitation, which is good, but does not state that the tool is read-only, safe, or any authorization needs. Adequate but not comprehensive.
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 extremely concise, with two sentences that convey purpose, filtering, ordering, and a technical constraint with no wasted words.
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?
For a list tool with no output schema, the description provides sufficient context: it lists bills, filtered by status, ordered by date. It does not detail return fields but is adequate for the tool's simplicity.
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 100%, so baseline is 3. The description adds value by listing common StatusID values (118, 178/179, 109/167) and the default limit, going beyond the schema.
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 the tool lists bills filtered by StatusID with specific ordering. It distinguishes from siblings like list-recent-bills-by-stage (different filter) and search-bills-by-name (different action).
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 explains the ordering rationale but does not explicitly state when to use this tool over alternatives or when not to use it. It provides clear context but lacks exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List bills by type (private, government, or committee), optionally filtered by Knesset number, ordered by most recent update.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max bills to return (default 20) | |
| billType | Yes | Bill origin type | |
| knessetNum | No | Optional Knesset number to filter by |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits. It mentions ordering by most recent update, but lacks details on pagination, default limit, error behavior, or any impact on data. This leaves the agent with significant unknowns for a read tool.
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 a single sentence that is front-loaded and to the point. Every word adds value: verb, resource, enum list, optional filter, ordering. No extraneous information.
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 the tool has 3 parameters and no output schema, the description is minimal. It covers the core functionality but lacks completeness on return format, limit default, and edge cases. Could benefit from mentioning result structure or default limit.
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 100% with descriptions for all three parameters. The description adds context that bills are grouped by type and optionally filtered by Knesset number, but does not provide additional syntax or format specifics beyond what the schema already offers. Baseline 3 is appropriate.
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 the verb 'List' and resource 'bills by type', includes the three enum values, optional Knesset filter, and ordering. It distinguishes from siblings like 'list-bills-by-status' by focusing on bill type, but does not explicitly differentiate from 'list-recent-bills-by-stage'.
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?
No guidance on when to use this tool versus alternatives. No mention of prerequisites, exclusions, or comparison with siblings like 'search-bills-by-name' or 'get-bill-info'. The description only states what it does, not when to choose it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List committees for a given Knesset number.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max committees to return (default 100) | |
| knessetNum | Yes | Knesset number | |
| onlyCurrent | No | If true, only currently active committees |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description does not disclose behavioral traits like side effects, rate limits, or return format. Only states basic function.
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?
Single sentence with no wasted words, appropriately short and front-loaded.
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?
Lacks output schema and fails to describe return format, pagination, or any additional context beyond the basic purpose.
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 has 100% parameter description coverage; description adds no extra meaning beyond schema definitions. Baseline 3 applies.
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?
Description clearly states verb 'list' and resource 'committees' with required parameter. Differentiates from siblings like get-committee-info and list-factions.
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?
No guidance on when to use this tool versus alternatives such as get-committee-info. Lacks context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List factions (parties) for a given Knesset number. Use the returned FactionID with list-knesset-members to get party rosters.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max factions to return (default 50) | |
| knessetNum | Yes | Knesset number | |
| onlyCurrent | No | If true, only currently active factions |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It does not disclose whether the operation is read-only, any side effects, auth requirements, or rate limits. For a list operation, this is a moderate gap.
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 extremely concise: two sentences with no wasted words. The key purpose and usage guidance are front-loaded.
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 no output schema, the description could have mentioned return fields (e.g., list of factions with FactionID, name). However, the context from sibling tools and the explicit pointer to list-knesset-members provides adequate completeness for a simple list 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?
The input schema has 100% description coverage, so the baseline is 3. The description adds some value by mentioning the use of FactionID with another tool, but does not add new meaning beyond the schema.
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 the verb (list), resource (factions), and condition (given Knesset number). It distinguishes from sibling tools like list-committees and list-knesset-members by specifying its scope.
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 when to use (for a given Knesset number) and provides a follow-up action (use returned FactionID with list-knesset-members). However, it lacks explicit exclusion of alternatives or when-not-to-use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List Knesset members (MKs) with party (faction) affiliation for a given Knesset. Uses PositionID=54 on KNS_PersonToPosition, which is the row that carries FactionID/FactionName (PositionID=43 exists but has null faction fields). Optionally filter by factionId — use list-factions to discover IDs. Note: an MK who switched factions mid-term appears once per stint.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max members to return (default 150) | |
| factionId | No | Optional KNS_Faction FactionID to filter to one party | |
| knessetNum | Yes | Knesset number | |
| onlyCurrent | No | If true, only current memberships (IsCurrent=true) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses internal data model choices (PositionID=54 vs 43), the behavior for mid-term switches, and optional filtering. This goes beyond a simple 'list members' description, though it does not cover potential rate limits or output format details.
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 concise with three sentences, front-loading the purpose in the first sentence. Every sentence adds necessary information without redundancy.
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 the tool has 4 parameters and no output schema, the description covers the main purpose, filtering options, and important data model nuances. However, it could mention default limit or pagination behavior (though limit is described in schema). Overall, it is 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.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description adds value for the factionId parameter by linking to list-factions, but for other parameters (knessetNum, limit, onlyCurrent) it adds little beyond the schema descriptions. The overall gain is marginal, so score remains 3.
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 the verb 'List' and resource 'Knesset members with party affiliation for a given Knesset.' It distinguishes from sibling tools like list-factions by explaining internal data model details (PositionID=54 vs 43), making the tool's specific role unambiguous.
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 provides context on when to use the tool (list MKs for a Knesset) and references list-factions to discover faction IDs for filtering. It also explains a behavioral nuance (switched MKs appear per stint), which aids correct usage. However, it does not explicitly state when not to use this tool or directly contrast with all sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List recent bills at a named legislative stage. Note: the Knesset combines 2nd and 3rd readings into one vote, so 'second-third-approved' is the closest proxy to 'passed second reading'. 'passed' = became law.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max bills to return (default 10) | |
| stage | Yes | Legislative stage | |
| knessetNum | No | Optional Knesset number to filter by |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It only states 'List recent bills' without explaining how recency is determined, pagination, authentication needs, or any side effects. The note on stage semantics is helpful but not about tool behavior.
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 extremely concise: two sentences that cover the core purpose and a critical nuance. Every word earns its place.
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?
Despite the schema covering parameters, the description lacks context on return format, ordering (what 'recent' means), and prerequisites. For a list tool with no output schema, the description should provide more detail about what the agent can expect.
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 100%, so parameters are already documented. The description adds value by explaining the stage enum values (e.g., 'second-third-approved' as proxy for passed second reading), which is not in the schema description for the stage parameter.
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 the action (list recent bills) and the filter criterion (named legislative stage). It does not explicitly differentiate from sibling tools like list-bills-by-status, but the stage-specific focus is evident.
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 provides explicit guidance on interpreting the stage values, especially clarifying the meaning of 'second-third-approved' and 'passed'. However, it does not discuss when to use this tool versus alternatives or provide exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search bills by keyword in their name. Returns up to 20 most recent Knesset matches.
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | Yes | Keyword to search for in bill names | |
| knessetNum | No | Optional Knesset number to filter by |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the result limit (up to 20) and recency (most recent), but does not mention authentication requirements, rate limits, or whether the operation is idempotent. As a search tool, the behavioral profile is mostly obvious, but the description adds minimal extra context.
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 consists of two concise sentences with clear front-loading. Every word is purposeful and no extraneous information is present.
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?
The tool has 2 well-documented parameters and no output schema. The description states it returns 'Knesset matches' but does not specify what fields are included (e.g., bill ID, name, status). Given the lack of output schema, the description should provide more detail about return values to be fully complete.
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 description coverage is 100%, so baseline is 3. The description adds no new meaning beyond the schema; it reiterates that the keyword searches bill names. No value is added for parameters like knessetNum.
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 the tool searches bills by keyword in their name and returns up to 20 most recent Knesset matches. The verb 'search' and resource 'bills by name' are specific, and the behavior distinguishes from sibling tools that filter by status, type, or stage.
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 implies usage when a keyword is available to search bill names, but it does not explicitly state when not to use it or mention alternatives like list-bills-by-status or list-bills-by-type. The context is clear but lacks explicit exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.1.1get-bill-infoget-committee-infolist-bills-by-statuslist-bills-by-typelist-committeeslist-factionslist-knesset-memberslist-recent-bills-by-stagesearch-bills-by-nameEach tool has a clearly distinct purpose: get-bill-info and get-committee-info target single entities; list-bills-by-status, list-bills-by-type, and list-recent-bills-by-stage provide different filtering; list-committees, list-factions, list-knesset-members each cover specific lists; search-bills-by-name is a keyword search. No overlap causes confusion.
All tool names follow a verb_noun_with_hyphens pattern. 'get-' is used for single-item retrieval, 'list-' for multiple items, and 'search-' for keyword search. The pattern is consistent and predictable across all 9 tools.
9 tools is appropriate for a parliamentary data server. It covers the main entities (bills, committees, factions, members) without being overwhelming or too sparse.
The tool set covers core CRUD-like queries (read-only) for bills, committees, factions, and members. Minor gaps include no dedicated get-faction or get-member tool, but list endpoints with filters largely fill these needs.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Public Data Ukraine Mcp connects AI agents to real public APIs via MCP. Tools include
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
Automate 1,000+ services from any MCP-compatible AI agent: build Applets, run actions and queries.
Knowledge base MCP for AI agents on iknow.dev. Search, read, and maintain via OAuth.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/zohar/knesset-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
