How do I use vergabe-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., "@vergabe-mcp Find open IT tenders flagged as suitable for freelancers." 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.

de en es ja ko ru zh

vergabe-mcp

by jocks-studio

Overview Schema Related Servers Score Discussions

TypeScript

Hybrid

vergabe-mcp

npm

An MCP server for oeffentlichevergabe.de, the German federal public-tender portal. Germany publishes every public tender there and offers a bulk open-data export, but that export lags a day, ships as daily ZIPs, and cannot filter — you download everything and sort it out yourself. The portal's own search API can filter (CPV code, region, deadline window, the eForms "suitable for freelancers" flag) and is current the moment a notice goes live, but it is undocumented. This server wraps it, so any MCP client can search the live feed with real filters and pull a notice in the portal's domain model, in eForms XML, or in OCDS. Anonymous, no API key, no account.

The reverse-engineered API reference is in docs/API.md — it stands on its own if you want to call the endpoints directly instead of through MCP.

Install

Nothing to install; run it with npx.

Claude Code

claude mcp add vergabe -- npx vergabe-mcp

Claude Desktop — in claude_desktop_config.json:

{
  "mcpServers": {
    "vergabe": {
      "command": "npx",
      "args": ["vergabe-mcp"]
    }
  }
}

Any other stdio client

npx vergabe-mcp

Streamable HTTP, if your client wants a URL rather than a subprocess:

npx vergabe-mcp --http --port 3000

Related MCP server: germany-tenders

Tools

Tool	What it does
`search_tenders`	Search lots with flat parameters — free text, CPV prefixes, `suitableFor`, contract nature, NUTS region, platform, deadline and publication windows, paging, sort. Returns normalized results.
`get_tender`	One notice by id, as a curated `summary` (default) or verbatim `domain` JSON, `eforms` XML, or `ocds` JSON.
`search_tenders_raw`	The native `SELECT`/`FROM`/`WHERE`/`PAGE`/`ORDER` DSL, passed through and returned raw — for anything the curated tool does not express.
`lookup_code`	Resolve a CPV or NUTS code to its German or English description.
`get_export_url`	Build the bulk open-data export URL for a day or month, with the caveats attached.

All five are read-only; the server writes nothing, stores nothing on disk, and holds no credentials.

Resources. vergabe://api-reference serves the API document, so a client can read what the backend actually supports before composing a query. Templates cover single notices — vergabe://notice/{noticeId}, .../eforms, .../ocds — and vergabe://codelist/{list}/{code}.

Prompt. find-solo-tenders (args: keywords, cpv, maxDays) searches with the freelancer/self-employed flags, then walks the model through triaging candidates: person-days buried in the description, whether the near deadline is a request to participate or the offer itself, and the fact that an empty value field means nothing. That triage knowledge ships as a prompt rather than as scoring code, so you can argue with it.

Example

You: Find open IT tenders that are flagged as suitable for freelancers.

The model calls search_tenders with cpv: ["72"], suitableFor: ["freelance"], onlyActive: true. On 2026-08-17 that is 30 open lots, among them:

{
  "noticeId": "7c70692d-dfb9-4b96-b777-4a5539eaee50",
  "title": "Beschaffung einer Beratungsdienstleistung zur Fachberatung im Rahmen eines Identity and Access Management (IAM) Projektes für die Stadtwerke Bielefeld (SWB)",
  "lotTitle": "Beratungsdienstleistung zur Fachberatung im Rahmen eines Identity and Access Management (IAM) Projektes",
  "buyer": "Stadtwerke Bielefeld GmbH",
  "cpv": "72260000",
  "noticeType": "cn-standard",
  "nature": "services",
  "deadline": "2026-09-14T10:00:00+02:00",
  "published": "2026-08-12T00:00:00+02:00"
}

It then calls get_tender on the interesting ones to read the description, the estimated value, and the exclusion grounds before telling you which are worth a bid — that judgment is the model's job, and the server deliberately does not score anything.

Note the shape of the data in that result: the deadline on this one is deadlineReceiptRequests, a request to participate, not an offer deadline. The find-solo-tenders prompt exists because distinctions like that decide whether a tender is reachable.

Development

Node 20 or newer.

npm install
npm test            # vitest, no network
npm run typecheck
npm run lint        # biome

Integration tests hit the live portal and are skipped unless you ask for them:

VERGABE_LIVE=1 npm test

Commits follow Conventional Commits; release-please turns them into a release PR on main — merging that PR tags the release, writes the changelog, publishes to npm, and attaches the tarball to the GitHub release. The commit type decides the version bump.

License

MIT.

Available Tools

5 tools

get_export_urlBulk export URLA

Read-only

Builds the URL of the official bulk export for one day or month. The file is a large ZIP, so download it outside this server.

ParametersJSON Schema

Name	Required	Description	Default
`day`	No	YYYY-MM-DD, must already be closed.
`month`	No	YYYY-MM.
`format`	No		eforms.zip

Output Schema

ParametersJSON Schema

Name	Required	Description
`url`	Yes
`note`	Yes
`format`	Yes

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already provide readOnlyHint and openWorldHint. The description adds actionable advice: 'download it outside this server' due to the large ZIP size. This enhances transparency beyond the annotations, though it could mention rate limits or authentication requirements.

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 consists of two efficient sentences: the first states the core purpose, and the second provides a critical behavioral caveat. No redundant information, every word earns its place.

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?

The description covers the main purpose and a key usage note. However, it is missing clarity on whether 'day' and 'month' are mutually exclusive or what happens when both are omitted (all parameters optional). Output schema may fill gaps, but a small clarification would make the description fully self-contained.

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 high (67%), with clear format descriptions for 'day' and 'month' and an enum for 'format'. The tool description adds no further parameter meaning beyond what the schema already provides, so the 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 clearly states the verb ('Builds the URL') and the resource ('official bulk export for one day or month'). It distinguishes the tool from sibling tools like 'search_tenders' and 'get_tender' by focusing on bulk export URL generation.

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 does not provide any guidance on when to use this tool versus alternatives or how to choose between the 'day' and 'month' parameters. It only mentions a precondition ('must already be closed') without explaining the use case for each parameter option.

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

get_tenderGet one noticeA

Read-only

Fetches a single notice. 'summary' extracts the fields a bidder decides on (deadlines, lot values, suitableFor, document links); the other formats are returned verbatim.

ParametersJSON Schema

Name	Required	Description	Default
`format`	No	summary = curated extraction; domain/ocds = full JSON; eforms = original XML.	summary
`noticeId`	Yes	Notice identifier (UUID) from a search result.
`noticeVersion`	No	Version like '01'; defaults to the latest published one.

Output Schema

ParametersJSON Schema

Name	Required	Description
`raw`	No	Verbatim response body for the non-summary formats.
`uri`	Yes	Canonical resource URI for the same document.
`format`	Yes
`summary`	No	Only for format 'summary'.
`noticeId`	Yes

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already provide readOnlyHint and openWorldHint, correctly indicating no side effects and external data mutability. The description adds value by detailing the behavioral difference between formats: summary is a curated extraction, while other formats are returned verbatim. This goes beyond what annotations offer.

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 two sentences: the first states the core purpose, the second explains the critical format differentiation. No redundant information; every sentence earns its place. Highly front-loaded and efficient.

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 tool has few parameters (all described in schema), an output schema, and comprehensive annotations, the description covers the essential behavioral nuance of formats. It could mention the default version behavior or error handling, but the agent has sufficient information for correct invocation.

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?

Schema description coverage is 100%, so baseline is 3. The description adds meaningful context for the 'format' parameter by explaining what 'summary' extracts (deadlines, lot values, suitableFor, document links) and that other formats are verbatim. This enhances agent understanding beyond the schema's enum descriptions.

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 it fetches a single notice, uses a specific verb ('fetches'), and explains the key distinction between the 'summary' format (curated extraction of bidder-relevant fields) and other verbatim formats. This effectively distinguishes it from sibling search tools.

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?

While the description implies the tool is for retrieving a single notice after obtaining an ID from a search, it does not explicitly state when to use it versus alternatives like search_tenders. No exclusion criteria or alternative tools are mentioned, leaving the agent to infer usage context.

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

lookup_codeLook up a CPV or NUTS codeB

Read-only

Resolves a CPV or NUTS code to its official description.

ParametersJSON Schema

Name	Required	Default
`code`	Yes
`list`	Yes
`language`	No	de

Output Schema

ParametersJSON Schema

Name	Required	Description
`code`	Yes
`list`	Yes
`description`	No
`descriptionDefault`	No

TDQS

B3.1/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, indicating safe read-only operation with a known set of codes. The description adds no extra behavioral context beyond 'resolves to official description', which is consistent but not additional.

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

Conciseness3/5

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

The description is a single sentence with no wasted words, but it is under-specified rather than efficiently complete. It is concise but sacrifices necessary detail.

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

Completeness2/5

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

Given three parameters (two required, with enums) and an output schema, the description lacks context about code format, case sensitivity, or the nature of the official description. The output schema is not shown, but even with it, the description should provide usage context.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate. It mentions 'CPV or NUTS code' hinting at the 'list' and 'code' parameters, but does not explain the 'language' parameter or the expected format of the code. This is insufficient for three parameters with no schema descriptions.

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?

Description clearly states the verb 'resolves' and the resource 'CPV or NUTS code' to its 'official description'. It is distinct from siblings like 'search_tenders' which deal with tenders, not code resolution.

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?

No guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. The description only states what it does, not when or why to invoke it.

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

search_tendersSearch German public tendersA

Read-only

Searches lots on oeffentlichevergabe.de. Defaults to open lots of the competition notice types (cn-standard, cn-social, cn-desg, subco, qu-sy, pin-cfc-standard, pin-cfc-social), newest first. Use search_tenders_raw for anything this does not cover.

ParametersJSON Schema

Name	Required	Description	Default
`cpv`	No	CPV code prefixes, OR-ed, e.g. ['72', '7921'].
`nuts`	No	NUTS codes of the place of performance.
`page`	No
`sort`	No		publicationDate
`text`	No	Free-text query across the whole notice (allFreeText).
`maxValue`	No	Estimated value in EUR. Set on roughly 8.5% of lots.
`minValue`	No	Estimated value in EUR. Set on roughly 8.5% of lots.
`pageSize`	No
`platform`	No	Contracting platform host, e.g. 'evergabe-online.de'.
`textMode`	No	How `text` is matched: all words, any word, or substring.	all
`onlyActive`	No	Restrict to lots that are still open.
`noticeTypes`	No	eForms notice types; defaults to the competition set (cn-standard, qu-sy, …).
`suitableFor`	No	BT-726 business types the buyer marked the lot suitable for.
`deadlineAfter`	No	ISO date or datetime; keeps lots whose first deadline is later.
`sortDirection`	No		DESC
`contractNature`	No
`publishedSince`	No	ISO date or datetime, inclusive lower bound.
`publishedBefore`	No	ISO date or datetime, inclusive upper bound.
`deadlineAtLeastDaysAway`	No	Keep lots whose first deadline is at least N days out — bidding runway.

Output Schema

ParametersJSON Schema

Name	Required	Description
`page`	Yes
`total`	Yes
`results`	Yes
`pageSize`	Yes

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already provide readOnlyHint and openWorldHint. Description adds default filtering and sorting behavior, as well as the specific website. No contradictions. Adds useful context beyond 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?

Two sentences, front-loaded with core action and defaults. Second sentence provides key alternative. No wasted words.

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 19 optional parameters, an output schema that documents return values, and a sibling tool reference, the description is sufficiently complete. It covers the tool's purpose, defaults, and when to use an alternative.

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 74%, so the schema already documents most parameters. The description mentions defaults for onlyActive, noticeTypes, and sort, but these are already in the schema. No new parameter semantics beyond what schema provides.

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?

Specifically states it searches lots on oeffentlichevergabe.de with defaults (open lots, competition notice types, newest first). Clearly distinguishes from sibling search_tenders_raw by saying 'use for anything this does not cover'.

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?

Explicitly provides default behavior and references an alternative tool for cases not covered. This gives clear when-to-use guidance.

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

search_tenders_rawSearch with the native DSLA

Read-only

Posts a WHERE/FROM/PAGE/ORDER query to /bkmk/searches unchanged. Operators: =, >, >=, <, <=, IN, STARTS_WITH, CONTAINS, MATCH_ALL, MATCH_ANY, RANGE_DAYS. Fields on lots: allFreeText, description, allCpvCodes, allContractNatures, active, noticeType, suitableFor (freelance|selbst|startup|other-sme), estimatedValue ('150000 EUR'), publicationDate, firstDeadline, allDeadlines, allPlacesOfPerformanceNutsCodes, contractingPlatform, procedureType, procedureLegalBasis, procedureIdentifier. Text and temporal operators take exactly one operand; IN and STARTS_WITH OR a list. RANGE_DAYS n means field >= midnight Europe/Berlin of today + n days, not a window. See the vergabe://api-reference resource for the full contract.

ParametersJSON Schema

Name	Required	Description	Default
`FROM`	No	'notices' has a smaller field set, rejects active/suitableFor and ignores ORDER.	lots
`PAGE`	No
`ORDER`	No	Other fields answer HTTP 500.
`WHERE`	No
`SELECT`	No	'ALL' or a projection of field names.	ALL

Output Schema

ParametersJSON Schema

Name	Required	Description
`offset`	Yes
`elements`	Yes
`totalElements`	Yes

TDQS

A4.7/5.0

Behavior5/5

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

Annotations declare readOnlyHint=true and openWorldHint=true. The description aligns: it describes a read operation ('posts a query ... unchanged') and adds behavioral nuances not covered by annotations, such as: 'RANGE_DAYS n means field >= midnight Europe/Berlin of today + n days, not a window', 'Other fields answer HTTP 500' for ORDER, and operator operand constraints. No contradiction.

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 dense paragraph. It front-loads the core action and then dumps operators and fields. While every sentence adds value, the lack of bullet points or breaks may hinder quick scanning. However, it is not verbose and efficiently packs necessary information. Could be slightly more structured but still effective.

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 5 parameters (0 required), nested objects, an output schema, and high complexity, the description covers query structure, operator semantics, field lists, FROM variations, ORDER limitations, and provides a reference to a full contract. It addresses pagination implicitly via PAGE parameter, and mentions error behavior for ORDER. No major gaps for a power-user tool.

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 60%, but the description adds substantial meaning beyond the input schema. It enumerates all operators with their operand requirements (e.g., 'Text and temporal operators take exactly one operand; IN and STARTS_WITH OR a list'), lists all field names on lots with examples (e.g., 'estimatedValue (''150000 EUR'')'), and clarifies constraints like RANGE_DAYS behavior. This compensates for schema gaps and aids correct parameter construction.

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 states a specific action: 'Posts a WHERE/FROM/PAGE/ORDER query to /bkmk/searches unchanged.' It names the HTTP method (POST), the endpoint, the query structure, and lists operators and fields. This clearly distinguishes it from the sibling 'search_tenders' tool, which likely provides a simpler search interface.

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 extensive operator and field listings, guiding the agent on how to construct queries. It also notes that the 'notices' FROM value has a smaller field set. However, it does not explicitly compare with the sibling 'search_tenders' to state when to use this raw DSL version versus a simpler alternative. Missing explicit when-not or alternatives, but the detail implies usage for complex filtering.

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.

5 tool updatesv1.0.1Aug 18, 2026
- First observedget_export_url
- First observedget_tender
- First observedlookup_code
- First observedsearch_tenders
- First observedsearch_tenders_raw

Install Server

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

TDQS

A4/5.0

Disambiguation5/5

Each tool targets a distinct operation: searching tenders, fetching details, raw querying, code lookup, and export URL generation. There is no overlap between their purposes.

Naming Consistency5/5

All tool names follow a clear verb_noun pattern (search_tenders, get_tender, search_tenders_raw, lookup_code, get_export_url). The conventions are uniform and predictable.

Tool Count5/5

Five tools are well-scoped for a public procurement domain. Each tool addresses a necessary function without being excessive or insufficient.

Completeness4/5

Core workflows for searching, fetching, raw querying, code lookup, and export are covered. Minor gaps like bulk export download instructions are handled via external guidance, which is acceptable.

Maintenance

ActivityMaintained

ResponsivenessSyncing

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

Germany Tenders A
io.github.pipeworx-io
Germany public procurement MCP — official German government tenders (keyless).
Government Data Open Data
322
tenderapi-mcp A
io.github.IDNSIDNS
MCP server for French (BOAMP) + EU (TED) public procurement data via TenderAPI.
Government Data Open Data Search
31
mcp-ted B
io.github.lexsocket
TED MCP Server: Real-time EU public tenders access. https://www.lexsocket.ai/
Government Data Search Open Data
2
Ausschreibungsagenten Tender Search A
de.ausschreibungsagenten
Search public procurement notices from 17 sources across Germany, the EU and the UK. Read-only.
Government Data Open Data
61

Related MCP Servers

qune-tech/ocds-mcp
Government Data Search RAG Systems
qune-tech
A
license
A
quality
B
maintenance
MCP server for German public procurement data (OCDS). Semantic search, tender matching, and company profiles — all from your local LLM
Updated a month ago (2026-07-26 10:13 UTC)
10
5
MIT
germany-tenders
Government Data Open Data
pipeworx-io
A
license
Not graded
quality
C
maintenance
Access official German government public procurement tenders via MCP, with keyless access.
Updated 11 days ago (2026-08-26 17:09 UTC)
12
MIT
swiss-procurement-mcp
Government Data Open Data Search
malkreide
A
license
A
quality
A
maintenance
MCP server providing read access to Swiss public procurement data via the official simap.ch API, covering all cantons and the Confederation with intraday updates. It enables searching tenders, awards, construction codes, and procurement offices through natural language queries.
Updated 8 hours ago (2026-09-06 07:23 UTC)
9
MIT
vartoofficial
Open Data Search Documentation Access
volodeveth
F
license
Not graded
quality
B
maintenance
MCP server for Ukrainian public procurement (Prozorro) that exposes tools to search tenders, retrieve tender details and cards, list and read tender documents.
Updated a month ago (2026-08-05 11:27 UTC)
-

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/jocks-studio/vergabe-mcp'

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

vergabe-mcp

Install

Tools

Example

Development

License

Available Tools

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

vartoofficial

Latest Blog Posts

MCP directory API